Article(id=1325489947351855231, tenantId=1146029695717560320, journalId=1324759914146529478, issueId=1325489890678420381, articleNumber=null, orderNo=null, doi=10.7544/issn1000-1239.202550069, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=research-article, receivedDate=1738771200000, receivedDateStr=2025-02-06, revisedDate=1757952000000, revisedDateStr=2025-09-16, acceptedDate=1760112000000, acceptedDateStr=2025-10-11, onlineDate=1793951029861, onlineDateStr=2026-11-06, pubDate=1767196800000, pubDateStr=2026-01-01, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1793951029861, onlineIssueDateStr=2026-11-06, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1793951029861, creator=13701087609, updateTime=1793951029861, updator=13701087609, issue=Issue{id=1325489890678420381, tenantId=1146029695717560320, journalId=1324759914146529478, year='2026', volume='63', issue='1', pageStart='1', pageEnd='272', issueExtLink='null', onlineDate='null', pubDate='1767196800000', pubDateStr='2026-01-01', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1793951016348, creator='13701087609', updateTime=1793952522017, updator='13701087609', preIssue=null, nextIssue=null, articleTotal=null, ext={EN=IssueExt(id=1325496205974839692, tenantId=1146029695717560320, journalId=1324759914146529478, issueId=1325489890678420381, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1325496205974839693, tenantId=1146029695717560320, journalId=1324759914146529478, issueId=1325489890678420381, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null, downloadFileDto=null}, startPage=123, endPage=146, ext={EN=ArticleExt(id=1325489949075714176, articleId=1325489947351855231, tenantId=1146029695717560320, journalId=1324759914146529478, language=EN, title=Survey of Hallucination Detection Methods for Large Language Models, columnId=1325489891789910943, journalTitle=Journal of Computer Research and Development, columnName=Artificial Intelligence, runingTitle=null, highlight=null, articleAbstract=
In recent years, large language models (LLMs) have made significant strides in the field of natural language processing (NLP), demonstrating impressive capabilities in both language understanding and generation. However, despite these advancements, LLMs still face numerous challenges in practical applications. One such issue that has garnered extensive attention from both the academic and industrial communities is the problem of hallucinations. Effectively detecting hallucinations in large language models is a critical challenge for ensuring their reliable, secure, and trustworthy application in downstream tasks such as text generation. We provide a comprehensive review of methods for detecting hallucinations in large language models. Firstly, we introduce the concept of large language models and clarify the definition and classification of hallucinations. Then we systematically examine the characteristics of LLMs throughout their entire lifecycle, from construction to deployment, and delve into the mechanisms and causes of hallucinations. Secondly, based on practical application requirements and considering factors such as model transparency in different task scenarios, we categorize hallucination detection methods into two types: those for white-box models and those for black-box models. A focused review and in-depth comparison of these methods are provided. Then we analyze and summarize the current mainstream benchmarks for hallucination detection, laying a foundation for future research in this area. Finally, we identify various potential research directions and new challenges in the detection of hallucinations in large language models.
, authors=Zituo Li
1, Jianbin Sun
1, Guangzhou Chen
1, Xinyue Fang
2, 3, Ruijing Cui
1, Zhiliang Tian
2, 3, Zhen Huang
2, 3, Kewei Yang
1, authorsList=Zituo Li, Jianbin Sun, Guangzhou Chen, Xinyue Fang, Ruijing Cui, Zhiliang Tian, Zhen Huang, Kewei Yang, authorCompany=null, correspAuthors=null, authorNote=
born in 1999. PhD candidate. His main research interests include hallucination, security, and evaluation in LLMs
born in 1989. PhD, associate professor, master supervisor. His main research interests include system test and evaluation, and decision and analysis under uncertainty
born in 2003. PhD candidate. His main research interests include LLMs inference optimization, LLMs evaluation, and data stream mining. (chen_gz@nudt.edu.cn)
born in 2002. Master candidate. Her main research interests include natural language processing, large language models, and deep learning. (fangxinyue@nudt.edu.cn)
born in 1996. PhD candidate. His main research interests include causal inference, and equipment test and evaluation. (cuiruijing@nudt.edu.cn)
born in 1992. Associate professor. Member of CCF. His main research interests include LLMs and natural language processing. (tianzhiliang@nudt.edu.cn)
born in 1984. PhD, professor, PhD supervisor. Member of CCF. His main research interests include machine learning, natural language processing, and intelligent systems. (huangzhen@nudt.edu.cn)
born in 1977. PhD, professor, PhD supervisor. His main research interests include equipment test and evaluation, and defense acquisition and systems requirement modeling. (kayyang27@nudt.edu.cn)
, correspAuthorsNote=null, copyrightStatement=Copyright © 2026 Journal of Computer Research and Development. All rights reserved., copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=null, magXml=null, pdfUrl=null, pdf=null, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=null, mapNumber=null, fund=null), CN=ArticleExt(id=1325489963659309215, articleId=1325489947351855231, tenantId=1146029695717560320, journalId=1324759914146529478, language=CN, title=大语言模型幻觉检测方法综述, columnId=1325489892104483745, journalTitle=计算机研究与发展, columnName=人工智能, runingTitle=null, highlight=null, articleAbstract=
近年来,大语言模型(large language models,LLMs)在自然语言处理(natural language processing,NLP)等领域取得了显著进展,展现出强大的语言理解与生成能力。然而,在实际应用过程中,大语言模型仍然面临诸多挑战。其中,幻觉(hallucination)问题引起了学术界和工业界的广泛关注。如何有效检测大语言模型幻觉,成为确保其在文本生成等下游任务可靠、安全、可信应用的关键挑战。该研究着重对大语言模型幻觉检测方法进行综述:首先,介绍了大语言模型概念,进一步明确了幻觉的定义与分类,系统梳理了大语言模型从构建到部署应用全生命周期各环节的特点,并深入分析了幻觉的产生机制与诱因;其次,立足于实际应用需求,考虑到在不同任务场景下模型透明度的差异等因素,将幻觉检测方法划分为针对白盒模型和黑盒模型2类,并进行了重点梳理和深入对比;而后,分析总结了现阶段主流的幻觉检测基准,为后续开展幻觉检测奠定基础;最后,指出了大语言模型幻觉检测的各种潜在研究方法和新的挑战。
, authors=李自拓
1, 孙建彬
1, 陈广州
1, 方馨悦
2, 3, 崔瑞靖
1, 田植良
2, 3, 黄震
2, 3, 杨克巍
1, authorsList=李自拓, 孙建彬, 陈广州, 方馨悦, 崔瑞靖, 田植良, 黄震, 杨克巍, authorCompany=null, correspAuthors=null, authorNote=
 |
1999年生。博士研究生。主要研究方向为大语言模型幻觉、安全和评估 |
 |
1989年生。博士,副教授,硕士生导师。主要研究方向为系统试验与评价、不确定性决策分析 |
 |
2003年生。博士研究生。主要研究方向为大语言模型推理优化、大语言模型评估、数据流挖掘 |
 |
2002年生。硕士研究生。主要研究方向为自然语言处理、大语言模型、深度学习 |
 |
1996年生。博士研究生。主要研究方向为因果推断、装备试验与鉴定 |
 |
1992年生。副研究员。CCF会员。主要研究方向为大语言模型、自然语言处理 |
 |
1984年生。博士,教授,博士生导师。CCF会员。主要研究方向为机器学习、自然语言处理、智能系统 |
 |
1977年生。博士,教授,博士生导师。主要研究方向为装备试验和评估、国防采办与体系需求建模 |
, correspAuthorsNote=null, copyrightStatement=版权所有 © 2026 计算机研究与发展编辑部, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=HFxqjDJ+fFp3yXyqPC4PQQ==, magXml=rCHWgul5Z7E6lZhner7M3g==, pdfUrl=null, pdf=0A2GEWoaOkfkXlcyPrjFfw==, pdfFileSize=3319005, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=GdNBukMMRfHY+lEQXLsblw==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=YXH41sgyPHfFFWWFaVXPzQ==, mapNumber=null, fund=null)}, authors=[Author(id=1325489968264655019, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=lizituonudt@nudt.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1325489969145458861, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, authorId=1325489968264655019, language=EN, stringName=Zituo Li, firstName=Zituo, middleName=null, lastName=Li, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, address=
1College of Systems Engineering, National University of Defense Technology, Changsha 410073, bio={"content":"
born in 1999. PhD candidate. His main research interests include hallucination, security, and evaluation in LLMs
"}, bioImg=null, bioContent=
born in 1999. PhD candidate. His main research interests include hallucination, security, and evaluation in LLMs
, aboutCorrespAuthor=null), CN=AuthorExt(id=1325489969590055086, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, authorId=1325489968264655019, language=CN, stringName=李自拓, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, address=
1国防科技大学系统工程学院 长沙 410073, bio={"img":"iBP/og8+azGRDszI6z9UXA==","content":"
1999年生。博士研究生。主要研究方向为大语言模型幻觉、安全和评估
"}, bioImg=iBP/og8+azGRDszI6z9UXA==, bioContent=
1999年生。博士研究生。主要研究方向为大语言模型幻觉、安全和评估
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1325489965806792865, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, xref=1, ext=[AuthorCompanyExt(id=1325489965857124514, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, companyId=1325489965806792865, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1College of Systems Engineering, National University of Defense Technology, Changsha 410073), AuthorCompanyExt(id=1325489965882290339, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, companyId=1325489965806792865, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1国防科技大学系统工程学院 长沙 410073)])]), Author(id=1325489969984319664, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=sunjianbin@nudt.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1325489970399555762, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, authorId=1325489969984319664, language=EN, stringName=Jianbin Sun, firstName=Jianbin, middleName=null, lastName=Sun, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, address=
1College of Systems Engineering, National University of Defense Technology, Changsha 410073, bio={"content":"
born in 1989. PhD, associate professor, master supervisor. His main research interests include system test and evaluation, and decision and analysis under uncertainty
"}, bioImg=null, bioContent=
born in 1989. PhD, associate professor, master supervisor. His main research interests include system test and evaluation, and decision and analysis under uncertainty
, aboutCorrespAuthor=null), CN=AuthorExt(id=1325489970831569075, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, authorId=1325489969984319664, language=CN, stringName=孙建彬, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, address=
1国防科技大学系统工程学院 长沙 410073, bio={"img":"l3+z1Q7pdgRmaMy6Z93Ifw==","content":"
1989年生。博士,副教授,硕士生导师。主要研究方向为系统试验与评价、不确定性决策分析
"}, bioImg=l3+z1Q7pdgRmaMy6Z93Ifw==, bioContent=
1989年生。博士,副教授,硕士生导师。主要研究方向为系统试验与评价、不确定性决策分析
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1325489965806792865, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, xref=1, ext=[AuthorCompanyExt(id=1325489965857124514, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, companyId=1325489965806792865, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1College of Systems Engineering, National University of Defense Technology, Changsha 410073), AuthorCompanyExt(id=1325489965882290339, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, companyId=1325489965806792865, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1国防科技大学系统工程学院 长沙 410073)])]), Author(id=1325489971230027957, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, orderNo=2, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=chen_gz@nudt.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1325489971670429879, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, authorId=1325489971230027957, language=EN, stringName=Guangzhou Chen, firstName=Guangzhou, middleName=null, lastName=Chen, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, address=
1College of Systems Engineering, National University of Defense Technology, Changsha 410073, bio={"content":"
born in 2003. PhD candidate. His main research interests include LLMs inference optimization, LLMs evaluation, and data stream mining. (chen_gz@nudt.edu.cn)
"}, bioImg=null, bioContent=
born in 2003. PhD candidate. His main research interests include LLMs inference optimization, LLMs evaluation, and data stream mining. (chen_gz@nudt.edu.cn)
, aboutCorrespAuthor=null), CN=AuthorExt(id=1325489972077277368, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, authorId=1325489971230027957, language=CN, stringName=陈广州, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, address=
1国防科技大学系统工程学院 长沙 410073, bio={"img":"+vxcO09QAWjlE5V1QpriAQ==","content":"
2003年生。博士研究生。主要研究方向为大语言模型推理优化、大语言模型评估、数据流挖掘
"}, bioImg=+vxcO09QAWjlE5V1QpriAQ==, bioContent=
2003年生。博士研究生。主要研究方向为大语言模型推理优化、大语言模型评估、数据流挖掘
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1325489965806792865, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, xref=1, ext=[AuthorCompanyExt(id=1325489965857124514, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, companyId=1325489965806792865, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1College of Systems Engineering, National University of Defense Technology, Changsha 410073), AuthorCompanyExt(id=1325489965882290339, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, companyId=1325489965806792865, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1国防科技大学系统工程学院 长沙 410073)])]), Author(id=1325489972500902074, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, orderNo=3, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=fangxinyue@nudt.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1325489972916138173, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, authorId=1325489972500902074, language=EN, stringName=Xinyue Fang, firstName=Xinyue, middleName=null, lastName=Fang, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
2, 3, address=
2College of Computer Science and Technology, National University of Defense Technology, Changsha 410073
3National Key Laboratory of Parallel and Distributed Computing (National University of Defense Technology), Changsha 410073, bio={"content":"
born in 2002. Master candidate. Her main research interests include natural language processing, large language models, and deep learning. (fangxinyue@nudt.edu.cn)
"}, bioImg=null, bioContent=
born in 2002. Master candidate. Her main research interests include natural language processing, large language models, and deep learning. (fangxinyue@nudt.edu.cn)
, aboutCorrespAuthor=null), CN=AuthorExt(id=1325489973352345790, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, authorId=1325489972500902074, language=CN, stringName=方馨悦, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
2, 3, address=
2国防科技大学计算机学院 长沙 410073
3并行与分布计算全国重点实验室(国防科技大学) 长沙 410073, bio={"img":"UDm2S623+90RmRvE1BczWA==","content":"
2002年生。硕士研究生。主要研究方向为自然语言处理、大语言模型、深度学习
"}, bioImg=UDm2S623+90RmRvE1BczWA==, bioContent=
2002年生。硕士研究生。主要研究方向为自然语言处理、大语言模型、深度学习
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1325489966649847972, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, xref=2, ext=[AuthorCompanyExt(id=1325489967006363813, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, companyId=1325489966649847972, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
2College of Computer Science and Technology, National University of Defense Technology, Changsha 410073), AuthorCompanyExt(id=1325489967211884710, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, companyId=1325489966649847972, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
2国防科技大学计算机学院 长沙 410073)]), AuthorCompany(id=1325489967849418919, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, xref=3, ext=[AuthorCompanyExt(id=1325489967908139176, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, companyId=1325489967849418919, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
3National Key Laboratory of Parallel and Distributed Computing (National University of Defense Technology), Changsha 410073), AuthorCompanyExt(id=1325489967929110697, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, companyId=1325489967849418919, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
3并行与分布计算全国重点实验室(国防科技大学) 长沙 410073)])]), Author(id=1325489975856345280, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, orderNo=4, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=cuiruijing@nudt.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1325489976703594690, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, authorId=1325489975856345280, language=EN, stringName=Ruijing Cui, firstName=Ruijing, middleName=null, lastName=Cui, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, address=
1College of Systems Engineering, National University of Defense Technology, Changsha 410073, bio={"content":"
born in 1996. PhD candidate. His main research interests include causal inference, and equipment test and evaluation. (cuiruijing@nudt.edu.cn)
"}, bioImg=null, bioContent=
born in 1996. PhD candidate. His main research interests include causal inference, and equipment test and evaluation. (cuiruijing@nudt.edu.cn)
, aboutCorrespAuthor=null), CN=AuthorExt(id=1325489977076887747, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, authorId=1325489975856345280, language=CN, stringName=崔瑞靖, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, address=
1国防科技大学系统工程学院 长沙 410073, bio={"img":"CDmrmKBmiIT+0udUurum2Q==","content":"
1996年生。博士研究生。主要研究方向为因果推断、装备试验与鉴定
"}, bioImg=CDmrmKBmiIT+0udUurum2Q==, bioContent=
1996年生。博士研究生。主要研究方向为因果推断、装备试验与鉴定
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1325489965806792865, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, xref=1, ext=[AuthorCompanyExt(id=1325489965857124514, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, companyId=1325489965806792865, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1College of Systems Engineering, National University of Defense Technology, Changsha 410073), AuthorCompanyExt(id=1325489965882290339, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, companyId=1325489965806792865, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1国防科技大学系统工程学院 长沙 410073)])]), Author(id=1325489977504706757, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, orderNo=5, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=tianzhiliang@nudt.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1325489977940914376, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, authorId=1325489977504706757, language=EN, stringName=Zhiliang Tian, firstName=Zhiliang, middleName=null, lastName=Tian, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
2, 3, address=
2College of Computer Science and Technology, National University of Defense Technology, Changsha 410073
3National Key Laboratory of Parallel and Distributed Computing (National University of Defense Technology), Changsha 410073, bio={"content":"
born in 1992. Associate professor. Member of CCF. His main research interests include LLMs and natural language processing. (tianzhiliang@nudt.edu.cn)
"}, bioImg=null, bioContent=
born in 1992. Associate professor. Member of CCF. His main research interests include LLMs and natural language processing. (tianzhiliang@nudt.edu.cn)
, aboutCorrespAuthor=null), CN=AuthorExt(id=1325489979614441674, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, authorId=1325489977504706757, language=CN, stringName=田植良, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
2, 3, address=
2国防科技大学计算机学院 长沙 410073
3并行与分布计算全国重点实验室(国防科技大学) 长沙 410073, bio={"img":"4V+Fy9oIOUO4Z8IDiEdgwA==","content":"
1992年生。副研究员。CCF会员。主要研究方向为大语言模型、自然语言处理
"}, bioImg=4V+Fy9oIOUO4Z8IDiEdgwA==, bioContent=
1992年生。副研究员。CCF会员。主要研究方向为大语言模型、自然语言处理
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1325489966649847972, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, xref=2, ext=[AuthorCompanyExt(id=1325489967006363813, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, companyId=1325489966649847972, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
2College of Computer Science and Technology, National University of Defense Technology, Changsha 410073), AuthorCompanyExt(id=1325489967211884710, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, companyId=1325489966649847972, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
2国防科技大学计算机学院 长沙 410073)]), AuthorCompany(id=1325489967849418919, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, xref=3, ext=[AuthorCompanyExt(id=1325489967908139176, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, companyId=1325489967849418919, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
3National Key Laboratory of Parallel and Distributed Computing (National University of Defense Technology), Changsha 410073), AuthorCompanyExt(id=1325489967929110697, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, companyId=1325489967849418919, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
3并行与分布计算全国重点实验室(国防科技大学) 长沙 410073)])]), Author(id=1325489979719299276, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, orderNo=6, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=huangzhen@nudt.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1325489980465885391, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, authorId=1325489979719299276, language=EN, stringName=Zhen Huang, firstName=Zhen, middleName=null, lastName=Huang, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
2, 3, address=
2College of Computer Science and Technology, National University of Defense Technology, Changsha 410073
3National Key Laboratory of Parallel and Distributed Computing (National University of Defense Technology), Changsha 410073, bio={"content":"
born in 1984. PhD, professor, PhD supervisor. Member of CCF. His main research interests include machine learning, natural language processing, and intelligent systems. (huangzhen@nudt.edu.cn)
"}, bioImg=null, bioContent=
born in 1984. PhD, professor, PhD supervisor. Member of CCF. His main research interests include machine learning, natural language processing, and intelligent systems. (huangzhen@nudt.edu.cn)
, aboutCorrespAuthor=null), CN=AuthorExt(id=1325489980855955664, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, authorId=1325489979719299276, language=CN, stringName=黄震, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
2, 3, address=
2国防科技大学计算机学院 长沙 410073
3并行与分布计算全国重点实验室(国防科技大学) 长沙 410073, bio={"img":"Qld+5JTBYbRP1eiUBZT2qg==","content":"
1984年生。博士,教授,博士生导师。CCF会员。主要研究方向为机器学习、自然语言处理、智能系统
"}, bioImg=Qld+5JTBYbRP1eiUBZT2qg==, bioContent=
1984年生。博士,教授,博士生导师。CCF会员。主要研究方向为机器学习、自然语言处理、智能系统
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1325489966649847972, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, xref=2, ext=[AuthorCompanyExt(id=1325489967006363813, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, companyId=1325489966649847972, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
2College of Computer Science and Technology, National University of Defense Technology, Changsha 410073), AuthorCompanyExt(id=1325489967211884710, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, companyId=1325489966649847972, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
2国防科技大学计算机学院 长沙 410073)]), AuthorCompany(id=1325489967849418919, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, xref=3, ext=[AuthorCompanyExt(id=1325489967908139176, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, companyId=1325489967849418919, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
3National Key Laboratory of Parallel and Distributed Computing (National University of Defense Technology), Changsha 410073), AuthorCompanyExt(id=1325489967929110697, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, companyId=1325489967849418919, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
3并行与分布计算全国重点实验室(国防科技大学) 长沙 410073)])]), Author(id=1325489980944036050, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, orderNo=7, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=kayyang27@nudt.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1325489981715787989, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, authorId=1325489980944036050, language=EN, stringName=Kewei Yang, firstName=Kewei, middleName=null, lastName=Yang, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, address=
1College of Systems Engineering, National University of Defense Technology, Changsha 410073, bio={"content":"
born in 1977. PhD, professor, PhD supervisor. His main research interests include equipment test and evaluation, and defense acquisition and systems requirement modeling. (kayyang27@nudt.edu.cn)
"}, bioImg=null, bioContent=
born in 1977. PhD, professor, PhD supervisor. His main research interests include equipment test and evaluation, and defense acquisition and systems requirement modeling. (kayyang27@nudt.edu.cn)
, aboutCorrespAuthor=null), CN=AuthorExt(id=1325489982252658902, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, authorId=1325489980944036050, language=CN, stringName=杨克巍, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, address=
1国防科技大学系统工程学院 长沙 410073, bio={"img":"2bnCSV+p8kWYrYZUwAtqYw==","content":"
1977年生。博士,教授,博士生导师。主要研究方向为装备试验和评估、国防采办与体系需求建模
"}, bioImg=2bnCSV+p8kWYrYZUwAtqYw==, bioContent=
1977年生。博士,教授,博士生导师。主要研究方向为装备试验和评估、国防采办与体系需求建模
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1325489965806792865, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, xref=1, ext=[AuthorCompanyExt(id=1325489965857124514, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, companyId=1325489965806792865, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1College of Systems Engineering, National University of Defense Technology, Changsha 410073), AuthorCompanyExt(id=1325489965882290339, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, companyId=1325489965806792865, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1国防科技大学系统工程学院 长沙 410073)])])], keywords=[Keyword(id=1325489984639217879, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, language=EN, orderNo=1, keyword=hallucination detection), Keyword(id=1325489985092202712, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, language=EN, orderNo=2, keyword=large language model), Keyword(id=1325489985494855897, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, language=EN, orderNo=3, keyword=factual consistency), Keyword(id=1325489985897509082, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, language=EN, orderNo=4, keyword=text generation), Keyword(id=1325489986321133787, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, language=EN, orderNo=5, keyword=natural language processing (NLP)), Keyword(id=1325489986421797084, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, language=CN, orderNo=1, keyword=幻觉检测), Keyword(id=1325489988460228831, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, language=CN, orderNo=2, keyword=大语言模型), Keyword(id=1325489989265535200, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, language=CN, orderNo=3, keyword=事实一致性), Keyword(id=1325489989357809889, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, language=CN, orderNo=4, keyword=文本生成), Keyword(id=1325489990087618786, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, language=CN, orderNo=5, keyword=自然语言处理)], refs=[Reference(id=1325490016557871359, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=1, rfOrder=0, authorNames=null, journalName=null, refType=null, unstructuredReference=Min B, Ross H, Sulem E, et al. Recent advances in natural language processing via large pre-trained language models: A survey[J]. ACM Computing Surveys, 2023, 56(2): 1−40, articleTitle=null, refAbstract=null), Reference(id=1325490017019244800, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=2, rfOrder=1, authorNames=null, journalName=null, refType=null, unstructuredReference=Fan Lizhou, Li Lingyao, Ma Zihui, et al. A bibliometric review of large language models research from 2017 to 2023[J]. ACM Transactions on Intelligent Systems and Technology, 2024, 15(5): 1−25, articleTitle=null, refAbstract=null), Reference(id=1325490018621468929, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=3, rfOrder=2, authorNames=null, journalName=null, refType=null, unstructuredReference=Navigli R, Conia S, Ross B. Biases in large language models: Origins, inventory, and discussion[J]. ACM Journal of Data and Information Quality, 2023, 15(2): 1−21, articleTitle=null, refAbstract=null), Reference(id=1325490019951063298, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=4, rfOrder=3, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhao Xin Wayne, Zhou Kun, Li Junyi, et al. A survey of large language models[J]. arXiv preprint, arXiv: 2303.18223, 2023, articleTitle=null, refAbstract=null), Reference(id=1325490020735398147, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=5, rfOrder=4, authorNames=null, journalName=null, refType=null, unstructuredReference=陈慧敏, 刘知远, 孙茂松. 大语言模型时代的社会机遇与挑战[J]. 计算机研究与发展, 2024, 61(5): 1094−1103, articleTitle=null, refAbstract=null), Reference(id=1325490021536510212, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=5, rfOrder=5, authorNames=null, journalName=null, refType=null, unstructuredReference=Chen Huimin, Liu Zhiyuan, Sun Maosong. The social opportunities and challenges in the era of large language models[J]. Journal of Computer Research and Development, 2024, 61(5): 1094−1103 (in Chinese), articleTitle=null, refAbstract=null), Reference(id=1325490022044020998, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=6, rfOrder=6, authorNames=null, journalName=null, refType=null, unstructuredReference=叶文涛, 胡家齐, 王皓波, 等. 面向大语言模型安全部署的可信评估体系[J]. 计算机研究与发展, 2025, 62(7): 1668−1684, articleTitle=null, refAbstract=null), Reference(id=1325490024975839496, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=6, rfOrder=7, authorNames=null, journalName=null, refType=null, unstructuredReference=Ye Wentao, Hu Jiaqi, Wang Haobo, et al. A trusted evaluation system for safe deployment of large language models[J]. Journal of Computer Research and Development, 2025, 62(7): 1668−1684 (in Chinese), articleTitle=null, refAbstract=null), Reference(id=1325490025797923081, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=7, rfOrder=8, authorNames=null, journalName=null, refType=null, unstructuredReference=Kalai A T, Santosh S V. Calibrated language models must hallucinate[C]//Proc of the 56th Annual ACM Symp on Theory of Computing. New York: ACM, 2024: 160−171, articleTitle=null, refAbstract=null), Reference(id=1325490026238325002, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=8, rfOrder=9, authorNames=null, journalName=null, refType=null, unstructuredReference=Lin, Zichao, Guan Shuyan, Zhang Wending, et al. Towards trustworthy LLMs: A review on debiasing and dehallucinating in large language models[J]. Artificial Intelligence Review, 2024, 57(9): 1−50, articleTitle=null, refAbstract=null), Reference(id=1325490026649366796, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=9, rfOrder=10, authorNames=null, journalName=null, refType=null, unstructuredReference=虎嵩林, 李涓子, 秦兵, 等. 亦正亦邪大模型——大模型与安全专题导读[J]. 计算机研究与发展, 2024, 61(5): 1085−1093, articleTitle=null, refAbstract=null), Reference(id=1325490027081380109, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=9, rfOrder=11, authorNames=null, journalName=null, refType=null, unstructuredReference=Hu Songlin, Li Juanzi, Qin Bing, et al. The good and evil big model: A special topic on big models and security[J]. Journal of Computer Research and Development, 2024, 61(5): 1085−1093 (in Chinese), articleTitle=null, refAbstract=null), Reference(id=1325490028792656144, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=10, rfOrder=12, authorNames=null, journalName=null, refType=null, unstructuredReference=Venkit P N, Chakravorti T, Gupta V, et al. An audit on the perspectives and challenges of hallucinations in NLP[C]//Proc of the 2024 Conf on Empirical Methods in Natural Language Processing. Stroudsburg, PA: ACL, 2024: 6528−6548, articleTitle=null, refAbstract=null), Reference(id=1325490029514076433, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=11, rfOrder=13, authorNames=null, journalName=null, refType=null, unstructuredReference=李煦, 朱睿, 陈小磊, 等. 视觉语言大模型的幻觉综述: 成因、评估与治理[J]. 计算机研究与发展, 2025, 62(12):2929−2950, articleTitle=null, refAbstract=null), Reference(id=1325490030365520146, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=11, rfOrder=14, authorNames=null, journalName=null, refType=null, unstructuredReference=Li Xu, Zhu Rui, Chen Xiaolei, et al. A survey of hallucinations in large vision-language models: Causes, evaluations and mitigations[J]. Journal of Computer Research and Development, 2025, 62(12):2929−2950 (in Chinese), articleTitle=null, refAbstract=null), Reference(id=1325490030856253716, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=12, rfOrder=15, authorNames=null, journalName=null, refType=null, unstructuredReference=Dahl M, Varun M, Mirac S, et al. Large legal fictions: Profiling legal hallucinations in large language models[J]. Journal of Legal Analysis, 2024, 16(1): 64−93, articleTitle=null, refAbstract=null), Reference(id=1325490032013881621, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=13, rfOrder=16, authorNames=null, journalName=null, refType=null, unstructuredReference=Liu Zhuang, Huang Ddegen, Huang Kaiyu, et al. FinBERT: A pre-trained financial language representation model for financial text mining[C]//Proc of the 29th Int Joint Conf on Artificial Intelligence. San Mateo, CA: Morgan Kaufmann, 2021: 4513−4519, articleTitle=null, refAbstract=null), Reference(id=1325490033695797528, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=14, rfOrder=17, authorNames=null, journalName=null, refType=null, unstructuredReference=刘泽垣, 王鹏江, 宋晓斌, 等. 大语言模型的幻觉问题研究综述[J]. 软件学报, 2025, 36(3): 1152−1185, articleTitle=null, refAbstract=null), Reference(id=1325490034169753881, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=14, rfOrder=18, authorNames=null, journalName=null, refType=null, unstructuredReference=Liu Zeyuan, Wang Pengjiang, Song Xiaobin, et al. Survey on hallucinations in large language models[J]. Journal of Software, 2025, 36(3): 1152−1185 (in Chinese), articleTitle=null, refAbstract=null), Reference(id=1325490035381907738, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=15, rfOrder=19, authorNames=null, journalName=null, refType=null, unstructuredReference=Ji Ziwei, Lee N, Frieske R, et al. Survey of hallucination in natural language generation[J]. ACM Computing Surveys, 2023, 55(12): 1−38, articleTitle=null, refAbstract=null), Reference(id=1325490036753445149, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=16, rfOrder=20, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhang Yue, Li Yafu, Cui Leyang, et al. Siren’s song in the AI ocean: A survey on hallucination in large language models[J]. arXiv preprint, arXiv: 2309.01219, 2023, articleTitle=null, refAbstract=null), Reference(id=1325490037973987614, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=17, rfOrder=21, authorNames=null, journalName=null, refType=null, unstructuredReference=Huang Lei, Yu Weijiang, Ma Weitao, et al. A survey on hallucination in large language models: Principles, taxonomy, challenges, and open questions[J]. ACM Transactions on Information Systems, 2025, 43(2): 1−55, articleTitle=null, refAbstract=null), Reference(id=1325490038850597151, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=18, rfOrder=22, authorNames=null, journalName=null, refType=null, unstructuredReference=Abbasi Yadkori Y, Kuzborskij I, György A, et al. To believe or not to believe your LLM: Iterative prompting for estimating epistemic uncertainty[C]//Proc of the 37th Int Conf on Neural Information Processing Systems. New York: Curran Associates, 2024: 58077−58117, articleTitle=null, refAbstract=null), Reference(id=1325490040448626976, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=19, rfOrder=23, authorNames=null, journalName=null, refType=null, unstructuredReference=Wu Junchao, Shu Yang, Zhan Runzhe, et al. A survey on LLM-generated text detection: Necessity, methods, and future directions[J]. Computational Linguistics, 2025, 51(1): 275−338, articleTitle=null, refAbstract=null), Reference(id=1325490042159903010, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=20, rfOrder=24, authorNames=null, journalName=null, refType=null, unstructuredReference=Black S, Biderman S, Hallahan E, et al. GPT-NeoX−20B: An open-source autoregressive language model[J]. arXiv preprint, arXiv: 2204.06745, 2022, articleTitle=null, refAbstract=null), Reference(id=1325490042596110627, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=21, rfOrder=25, authorNames=null, journalName=null, refType=null, unstructuredReference=Sun Weiwei, Shi Zhengliang, Gao Shen, et al. Contrastive learning reduces hallucination in conversations[C]//Proc of the 37th AAAI Conf on Artificial Intelligence. Palo Alto, CA: AAAI, 2023: 13618−13626, articleTitle=null, refAbstract=null), Reference(id=1325490043804070180, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=22, rfOrder=26, authorNames=null, journalName=null, refType=null, unstructuredReference=Chen Sihao, Zhang Fan, Sone K, et al. Improving faithfulness in abstractive summarization with contrast candidate generation and selection[C]//Proc of the 2019 Conf of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Stroudsburg, PA: ACL, 2021: 5935−5941, articleTitle=null, refAbstract=null), Reference(id=1325490045033001254, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=23, rfOrder=27, authorNames=null, journalName=null, refType=null, unstructuredReference=Dziri N, Madotto A, Zaiane O, et al. Neural path hunter: Reducing hallucination in dialogue systems via path grounding[C]//Proc of the 2021 Conf on Empirical Methods in Natural Language Processing. Stroudsburg, PA: ACL, 2021: 2197−2214, articleTitle=null, refAbstract=null), Reference(id=1325490046727500072, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=24, rfOrder=28, authorNames=null, journalName=null, refType=null, unstructuredReference=Huang Yichong, Feng Xiachong, Feng Xiaocheng. The factual inconsistency problem in abstractive text summarization: A survey[J]. arXiv preprint, arXiv: 2104.14839, 2023, articleTitle=null, refAbstract=null), Reference(id=1325490047981596969, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=25, rfOrder=29, authorNames=null, journalName=null, refType=null, unstructuredReference=Chen Xinxi, Wang Li, Wu Wei, et al. Honest AI: Fine-tuning “small” language models to say “I Don’t Know”, and reducing hallucination in RAG[J]. arXiv preprint, arXiv: 2410.09699, 2024, articleTitle=null, refAbstract=null), Reference(id=1325490048442970410, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=26, rfOrder=30, authorNames=null, journalName=null, refType=null, unstructuredReference=Huang Yizheng, Huang J. A survey on retrieval-augmented text generation for large language models[J]. arXiv preprint, arXiv: 2404.10981, 2024, articleTitle=null, refAbstract=null), Reference(id=1325490049260859691, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=27, rfOrder=31, authorNames=null, journalName=null, refType=null, unstructuredReference=Xie Jinheng, Mao Weijia, Bai Zechen, et al. Show-o: One single transformer to unify multimodal understanding and generation[J]. arXiv preprint, arXiv: 2408.12528, 2024, articleTitle=null, refAbstract=null), Reference(id=1325490051064410413, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=28, rfOrder=32, authorNames=null, journalName=null, refType=null, unstructuredReference=Vaswani A, Shazeer N, Parmar N, et al. Attention is all you need[C]//Proc of the 30th Int Conf on Neural Information Processing Systems. New York: Curran Associates, 2017: 5998−6008, articleTitle=null, refAbstract=null), Reference(id=1325490051752276272, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=29, rfOrder=33, authorNames=null, journalName=null, refType=null, unstructuredReference=Devlin J, Chang M W, Lee K, et al. BERT: Pre-training of deep bidirectional Transformers for language understanding[C]//Proc of the 2019 Conf of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Stroudsburg, PA: ACL, 2019: 4171−4186, articleTitle=null, refAbstract=null), Reference(id=1325490052213649713, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=30, rfOrder=34, authorNames=null, journalName=null, refType=null, unstructuredReference=Radford, A, Narasimhan T, Salimans I, et al. Improving language understanding by generative pre-training[EB/OL]. (2018-06-11)[2024-12-21]. https://openai.com/index/language-unsupervised/, articleTitle=null, refAbstract=null), Reference(id=1325490052658245938, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=31, rfOrder=35, authorNames=null, journalName=null, refType=null, unstructuredReference=Radford A, Wu J, Child R, et al. Language models are unsupervised multitask learners[EB/OL]. [2024-12-21]. https://cdn.openai.com/better-language-models/language_models_are_unsupervised_multitask_learners.pdf, articleTitle=null, refAbstract=null), Reference(id=1325490053429997875, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=32, rfOrder=36, authorNames=null, journalName=null, refType=null, unstructuredReference=Brown T, Mann B, Ryder N, et al. Language models are few-shot learners[C]//Proc of the 33rd Advances in Neural Information Processing Systems. Cambridge, MA: MIT, 2020: 1877−1901, articleTitle=null, refAbstract=null), Reference(id=1325490055569092916, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=33, rfOrder=37, authorNames=null, journalName=null, refType=null, unstructuredReference=OpenAI. GPT-4 technical report[J]. arXiv preprint, arXiv: 2305. 10403, 2023, articleTitle=null, refAbstract=null), Reference(id=1325490056454091064, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=34, rfOrder=38, authorNames=null, journalName=null, refType=null, unstructuredReference=Raffel C, Shazeer N, Roberts A, et al. Exploring the limits of transfer learning with a unified text-to-text Transformer[J]. Machine Learning Research, 2020, 21(140): 1−67., articleTitle=null, refAbstract=null), Reference(id=1325490057255203129, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=35, rfOrder=39, authorNames=null, journalName=null, refType=null, unstructuredReference=Yang Zhilin, Dai Zihang, Yang Yiming, et al. XLNet: Generalized autoregressive pretraining for language understanding[J]. arXiv preprint, arXiv: 1906.08237, 2019, articleTitle=null, refAbstract=null), Reference(id=1325490057624301882, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=36, rfOrder=40, authorNames=null, journalName=null, refType=null, unstructuredReference=Elaraby M, Lu Mengyin, Dunn J, et al. HaLo: Estimation and reduction of hallucinations in open-source weak large language models[J]. arXiv preprint, arXiv: 21308.11764, 2023, articleTitle=null, refAbstract=null), Reference(id=1325490058479939899, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=37, rfOrder=41, authorNames=null, journalName=null, refType=null, unstructuredReference=Touvron H, Lavril T, Izacard G, et al. LLaMA: Open and efficient foundation language models[J]. arXiv preprint, arXiv: 2302.13971, 2023, articleTitle=null, refAbstract=null), Reference(id=1325490060149272892, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=38, rfOrder=42, authorNames=null, journalName=null, refType=null, unstructuredReference=Yin Ziqi, Zhang Mingxin, Kawahara D. Harmony: A home agent for responsive management and action optimization with a locally deployed large language model[J]. arXiv preprint, arXiv: 2410.14252, 2024, articleTitle=null, refAbstract=null), Reference(id=1325490060564508989, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=39, rfOrder=43, authorNames=null, journalName=null, refType=null, unstructuredReference=Li Zuchao, Zhang Shitou, Zhao Hai, et al. BatGPT: A bidirectional autoregessive talker from generative pre-trained transformer[J]. arXiv preprint, arXiv: 2307.00360, 2023, articleTitle=null, refAbstract=null), Reference(id=1325490061441118526, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=40, rfOrder=44, authorNames=null, journalName=null, refType=null, unstructuredReference=DeRose J F, Wang Jjiayao, Berger M. Attention flows: Analyzing and comparing attention mechanisms in language models[J]. IEEE Transactions on Visualization and Computer Graphics, 2020, 27(2): 1160−1170, articleTitle=null, refAbstract=null), Reference(id=1325490062670049599, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=41, rfOrder=45, authorNames=null, journalName=null, refType=null, unstructuredReference=Saxena A, Bhattacharyya P. Hallucination detection in machine generated text: A survey[EB/OL]. (2025-01-21)[2025-01-22]. https://www.cfilt.iitb.ac.in/resources/surveys/2024/survey_ashita_hallucination_detection_in_machine_generated_text_2024.pdf, articleTitle=null, refAbstract=null), Reference(id=1325490065169854784, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=42, rfOrder=46, authorNames=null, journalName=null, refType=null, unstructuredReference=Hahn M. Theoretical limitations of selfattention in neural sequence models[J]. Transactions of the Association for Computational Linguistics, 2020, 8: 156−171, articleTitle=null, refAbstract=null), Reference(id=1325490067250229569, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=43, rfOrder=47, authorNames=null, journalName=null, refType=null, unstructuredReference=Chiang D, Cholak P. Overcoming a theoretical limitation of self-attention[C]//Proc of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Stroudsburg, PA: ACL, 2022: 7654−7664, articleTitle=null, refAbstract=null), Reference(id=1325490069351575874, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=44, rfOrder=48, authorNames=null, journalName=null, refType=null, unstructuredReference=Naveed H, Khan A U, Qiu Shi, et al. A comprehensive overview of large language models[J]. arXiv preprint arXiv: 2307.06435, 2023, articleTitle=null, refAbstract=null), Reference(id=1325490070291099971, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=45, rfOrder=49, authorNames=null, journalName=null, refType=null, unstructuredReference=Annepaka Y, Pakray P. Large language models: A survey of their development, capabilities, and applications[J]. Knowledge and Information Systems, 2025, 67(3): 2967−3022, articleTitle=null, refAbstract=null), Reference(id=1325490071457116485, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=46, rfOrder=50, authorNames=null, journalName=null, refType=null, unstructuredReference=Xu Weijia, Agrawal S, Briakou E, et al. Understanding and detecting hallucinations in neural machine translation via model introspection[J]. Transactions of the Association for Computational Linguistics, 2023, 11: 546−564, articleTitle=null, refAbstract=null), Reference(id=1325490073600405830, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=47, rfOrder=51, authorNames=null, journalName=null, refType=null, unstructuredReference=Filippova K. Controlled hallucinations: Learning to generate faithfully from noisy data[C]//Proc of the Findings of the Association for Computational Linguistics: EMNLP 2020. Stroudsburg, PA: ACL, 2020: 864−870, articleTitle=null, refAbstract=null), Reference(id=1325490074456043848, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=48, rfOrder=52, authorNames=null, journalName=null, refType=null, unstructuredReference=Nicholas C, Tramer F, Wallace E, et al. Extracting training data from large language models[C]//Proc of the 30th USENIX Security Symp. Berkeley, CA: USENIX Association, 2021: 2633−2650, articleTitle=null, refAbstract=null), Reference(id=1325490074837725513, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=49, rfOrder=53, authorNames=null, journalName=null, refType=null, unstructuredReference=Carlini N, Ippolito D, Jagielski M, et al. Quantifying memorization across neural language models[J]. arXiv preprint, arXiv: 2202.07646, 2022, articleTitle=null, refAbstract=null), Reference(id=1325490075735306571, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=50, rfOrder=54, authorNames=null, journalName=null, refType=null, unstructuredReference=Chowdhery A, Narang S, Devlin J, et al. Palm: Scaling language modeling with pathways[J]. Journal of Machine Learning Research, 2023, 24(240): 1−13, articleTitle=null, refAbstract=null), Reference(id=1325490077824069964, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=51, rfOrder=55, authorNames=null, journalName=null, refType=null, unstructuredReference=Lee K, Ippolito D, Nystrom A, et al. Deduplicating training data makes language models better[C]//Proc of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Stroudsburg, PA: ACL, 2022: 8424−8445, articleTitle=null, refAbstract=null), Reference(id=1325490079073972557, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=52, rfOrder=56, authorNames=null, journalName=null, refType=null, unstructuredReference=Kandpal N, Deng Haikang, Roberts A, et al. Large language models struggle to learn long-tail knowledge[C]//Proc of the 40th Int Conf on Machine Learning. New York: PMLR, 2023: 15696−15707, articleTitle=null, refAbstract=null), Reference(id=1325490080340652366, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=53, rfOrder=57, authorNames=null, journalName=null, refType=null, unstructuredReference=Hernandez D, Brown T, Conerly T, et al. Scaling laws and interpretability of learning from repeated data[J]. arXiv preprint, arXiv: 2205.10487, 2022, articleTitle=null, refAbstract=null), Reference(id=1325490081141764431, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=54, rfOrder=58, authorNames=null, journalName=null, refType=null, unstructuredReference=陈晋音, 陈奕芃, 陈一鸣, 等. 面向深度学习的公平性研究综述[J]. 计算机研究与发展, 2021, 58(2): 264−280, articleTitle=null, refAbstract=null), Reference(id=1325490082811097424, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=54, rfOrder=59, authorNames=null, journalName=null, refType=null, unstructuredReference=Chen Jinyin, Chen Yipeng, Chen Yiming, et al. Fairness research on deep learning[J]. Journal of Computer Research and Development, 2021, 58(2): 264−280 (in Chinese), articleTitle=null, refAbstract=null), Reference(id=1325490083645763921, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=55, rfOrder=60, authorNames=null, journalName=null, refType=null, unstructuredReference=Sheng E, Chang Kaiwei, Natarajan P, et al. Societal biases in language generation: Progress and challenges[C]//Proc of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th Int Joint Conf on Natural Language Processing (Volume 1: Long Papers). Stroudsburg, PA: ACL, 2021: 4275−4293, articleTitle=null, refAbstract=null), Reference(id=1325490084522373458, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=56, rfOrder=61, authorNames=null, journalName=null, refType=null, unstructuredReference=Wan Yixin, Pu G, Sun Jiao, et al. “Kelly is a warm person, Joseph is a role model”: Gender biases in LLM-generated reference letters[C]//Proc of the Findings of the Association for Computational Linguistics: EMNLP 2023. Stroudsburg, PA: ACL, 2023: 3730−3748, articleTitle=null, refAbstract=null), Reference(id=1325490085336068436, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=57, rfOrder=62, authorNames=null, journalName=null, refType=null, unstructuredReference=Karpowicz, M. On the fundamental impossibility of hallucination control in large language models[J]. arXiv preprint, arXiv: 2506.06382, 2025, articleTitle=null, refAbstract=null), Reference(id=1325490087017984342, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=58, rfOrder=63, authorNames=null, journalName=null, refType=null, unstructuredReference=Liu Yinqiu, Liu Guangyuan, Zhang Ruichen, et al. Hallucination-aware optimization for large language model-empowered communications[J]. arXiv preprint, arXiv: 2412.06007, 2024, articleTitle=null, refAbstract=null), Reference(id=1325490088284664151, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=59, rfOrder=64, authorNames=null, journalName=null, refType=null, unstructuredReference=Pal A, Umapathi L K, Sankarasubbu M. Med-HALT: Medical domain hallucination test for large language models[C]//Proc of the 27th Conf on Computational Natural Language Learning, Stroudsburg, PA: ACL, 2023: 314−334, articleTitle=null, refAbstract=null), Reference(id=1325490089580704088, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=60, rfOrder=65, authorNames=null, journalName=null, refType=null, unstructuredReference=Roychowdhury S. Journey of hallucination-minimized generative AI solutions for financial decision makers[C]//Proc of the 17th ACM Int Conf on Web Search and Data Mining. New York: ACM, 2024: 1180−1181, articleTitle=null, refAbstract=null), Reference(id=1325490091602358617, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=61, rfOrder=66, authorNames=null, journalName=null, refType=null, unstructuredReference=Wang Mengru, Yao Yunzhi, Xu Ziwen, et al. Knowledge mechanisms in large language models: A survey and perspective[C]//Proc of the Findings of the Association for Computational Linguistics: EMNLP 2024. Stroudsburg, PA: ACL, 2024: 7097−7135, articleTitle=null, refAbstract=null), Reference(id=1325490092445413722, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=62, rfOrder=67, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhang Ningyu, Yao Yunzhi, Tian Bozhong, et al. A comprehensive study of knowledge editing for large language models[J]. arXiv preprint, arXiv: 2401.01286, 2024, articleTitle=null, refAbstract=null), Reference(id=1325490092890009947, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=63, rfOrder=68, authorNames=null, journalName=null, refType=null, unstructuredReference=Feng Zhangyin, Ma Weitao, Yu Weijiang, et al. Trends in integration of knowledge and large language models: A survey and taxonomy of methods, benchmarks, and applications[J]. arXiv preprint, arXiv: 2311.05876, 2023, articleTitle=null, refAbstract=null), Reference(id=1325490093338800476, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=64, rfOrder=69, authorNames=null, journalName=null, refType=null, unstructuredReference=Schulman J. Reinforcement learning from human feedback: Progress and challenges[EB/OL]. [2025-01-01]. https://eecs.berkeley.edu/research/colloquium/230419-2/, articleTitle=null, refAbstract=null), Reference(id=1325490094567731550, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=65, rfOrder=70, authorNames=null, journalName=null, refType=null, unstructuredReference=Pal A, Sankarasubbu M. Gemini goes to med school: Exploring the capabilities of multimodal large language models on medical challenge problems & hallucinations[J]. arXiv preprint, arXiv: 2402.07023, 2024, articleTitle=null, refAbstract=null), Reference(id=1325490095960240480, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=66, rfOrder=71, authorNames=null, journalName=null, refType=null, unstructuredReference=Wang Haochun, Zhao Sendong, Qiang Zewen, et al. Knowledge-tuning large language models with structured medical knowledge bases for trustworthy response generation in Chinese[J]. ACM Transactions on Knowledge Discovery from Data, 2025, 19(2): 1−17, articleTitle=null, refAbstract=null), Reference(id=1325490097449218402, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=67, rfOrder=72, authorNames=null, journalName=null, refType=null, unstructuredReference=Wei J, Huang Da, Lu Yifeng, et al. Simple synthetic data reduces sycophancy in large language models[J]. arXiv preprint, arXiv: 2308.03958, 2023, articleTitle=null, refAbstract=null), Reference(id=1325490098325827939, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=68, rfOrder=73, authorNames=null, journalName=null, refType=null, unstructuredReference=Sharma Mrinank, Tong M, Korbak T, et al. Towards understanding sycophancy in language models[J]. arXiv preprint, arXiv: 2310.13548, 2023, articleTitle=null, refAbstract=null), Reference(id=1325490100867576164, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=69, rfOrder=74, authorNames=null, journalName=null, refType=null, unstructuredReference=Perez E, Ringer S, Lukošiūtė K, et al. Discovering language model behaviors with model-written evaluations[C]//Proc of the 61st Annual Meeting of the Association for Computational Linguistics. Stroudsburg, PA: ACL, 2023: 13387−13434, articleTitle=null, refAbstract=null), Reference(id=1325490101328949605, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=70, rfOrder=75, authorNames=null, journalName=null, refType=null, unstructuredReference=Lu Taiming, Shen Lingfeng, Yang Xinyu, et al. It takes two: On the seamlessness between reward and policy model in RLHF[J]. arXiv preprint, arXiv: 2406.07971, 2024, articleTitle=null, refAbstract=null), Reference(id=1325490104638255462, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=71, rfOrder=76, authorNames=null, journalName=null, refType=null, unstructuredReference=Lee N, Wei Ping, Xu Peng, et al. Factuality enhanced language models for open-ended text generation[C]//Proc of the 35th Int Conf on Neural Information Processing Systems. New York: Curran Associates, 2022: 34586−34599, articleTitle=null, refAbstract=null), Reference(id=1325490105443561831, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=72, rfOrder=77, authorNames=null, journalName=null, refType=null, unstructuredReference=Renze M, Guven E. The effect of sampling temperature on problem solving in large language models[J]. arXiv preprint, arXiv: 2402.05201, 2024, articleTitle=null, refAbstract=null), Reference(id=1325490105913323880, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=73, rfOrder=78, authorNames=null, journalName=null, refType=null, unstructuredReference=Chang H S, Peng Nanyun, Bansal M, et al. Real sampling: Boosting factuality and diversity of open-ended generation via asymptotic entropy[J]. arXiv preprint, arXiv: 2406.07735, 2024, articleTitle=null, refAbstract=null), Reference(id=1325490107188392297, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=74, rfOrder=79, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhang Muru, Press O, Merrill W, et al. How language model hallucinations can snowball[J]. arXiv preprint, arXiv: 2305.13534, 2023, articleTitle=null, refAbstract=null), Reference(id=1325490109650448747, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=75, rfOrder=80, authorNames=null, journalName=null, refType=null, unstructuredReference=Kang Haoqiang, Ni Juntong, Yao Huaxiu. Ever: Mitigating hallucination in large language models through real-time verification and rectification[J]. arXiv preprint, arXiv: 2311.09114, 2023, articleTitle=null, refAbstract=null), Reference(id=1325490110522863980, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=76, rfOrder=81, authorNames=null, journalName=null, refType=null, unstructuredReference=Wei J, Wang Xuezhi, Schuurmans D, et al. Chain-of-thought prompting elicits reasoning in large language models[C]//Proc of the 35th Int Conf on Neural Information Processing Systems. New York: Curran Associates, 2022: 24824−24837, articleTitle=null, refAbstract=null), Reference(id=1325490111332364653, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=77, rfOrder=82, authorNames=null, journalName=null, refType=null, unstructuredReference=Kojima T, Gu S S, Reid M, et al. Large language models are zero-shot reasoners[C]//Proc of the 35th Int Conf on Neural Information Processing Systems. New York: Curran Associates, 2022: 22199−22213, articleTitle=null, refAbstract=null), Reference(id=1325490112565490030, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=78, rfOrder=83, authorNames=null, journalName=null, refType=null, unstructuredReference=Yee E, Li A, Tang Chenyu, et al. Faithful and unfaithful error recovery in chain of thought[EB/OL]. (2024-07-10)[2024-12-21]. https://openreview.net/forum?id=IPZ28ZqD4I, articleTitle=null, refAbstract=null), Reference(id=1325490114335486321, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=79, rfOrder=84, authorNames=null, journalName=null, refType=null, unstructuredReference=Agarwal C, Tanneru S H, Lakkaraju H. Faithfulness vs. plausibility: On the (un) reliability of explanations from large language models[J]. arXiv preprint, arXiv: 2402.04614, 2024, articleTitle=null, refAbstract=null), Reference(id=1325490115128209778, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=80, rfOrder=85, authorNames=null, journalName=null, refType=null, unstructuredReference=Turpin M, Michael J, Perez E, et al. Language models don’t always say what they think: unfaithful explanations in chain-of-thought prompting[C]//Proc of the 37th Int Conf on Neural Information Processing Systems. New York: Curran Associates, 2024: 74952−74965, articleTitle=null, refAbstract=null), Reference(id=1325490116348752243, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=81, rfOrder=86, authorNames=null, journalName=null, refType=null, unstructuredReference=Lanham T, Chen A, Radhakrishnan A, et al. Measuring faithfulness in chain-of-thought reasoning[J]. arXiv preprint, arXiv: 2307.13702, 2023, articleTitle=null, refAbstract=null), Reference(id=1325490118072611189, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=82, rfOrder=87, authorNames=null, journalName=null, refType=null, unstructuredReference=Chen Qiguang, Chen Libo, Liu Jinhao, et al. Towards reasoning era: A survey of long chain-of-thought for reasoning large language models[J]. arXiv preprint, arXiv: 2503.09567, 2025, articleTitle=null, refAbstract=null), Reference(id=1325490119280570742, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=83, rfOrder=88, authorNames=null, journalName=null, refType=null, unstructuredReference=Ren Ruiyang, Wang Yuhao, Qu Yingqi, et al. Investigating the factual knowledge boundary of large language models with retrieval augmentation[J]. arXiv preprint, arXiv: 2307.11019, 2023, articleTitle=null, refAbstract=null), Reference(id=1325490119708389751, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=84, rfOrder=89, authorNames=null, journalName=null, refType=null, unstructuredReference=Wen Bingbing, Xu Chenjun, Bin H A N, et al. Mitigating overconfidence in large language models: A behavioral lens on confidence estimation and calibration[C]//Proc of the 37th Advances in Neural Information Processing Systems Workshop. Cambridge, MA: MIT, 2024: 1877−1901, articleTitle=null, refAbstract=null), Reference(id=1325490120605970808, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=85, rfOrder=90, authorNames=null, journalName=null, refType=null, unstructuredReference=Niu Cheng, Wu Yuanhao, Zhu Juno, et al. Ragtruth: A hallucination corpus for developing trustworthy retrieval-augmented language models[J]. arXiv preprint, arXiv: 2401.00396, 2023, articleTitle=null, refAbstract=null), Reference(id=1325490122711511420, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=86, rfOrder=91, authorNames=null, journalName=null, refType=null, unstructuredReference=Hu Haichuan, Sun Yuhan, Zhang Quanjun. LRP4RAG: Detecting hallucinations in retrieval-augmented generation via layer-wise relevance propagation[J]. arXiv preprint, arXiv: 2408.15533, 2024, articleTitle=null, refAbstract=null), Reference(id=1325490123458097533, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=87, rfOrder=92, authorNames=null, journalName=null, refType=null, unstructuredReference=Barnett S, Kurniawan S, Thudumu S, et al. Seven failure points when engineering a retrieval augmented generation system[C]//Proc of the 3rd IEEE/ACM Int Conf on AI Engineering-Software Engineering for AI. Piscataway, NJ: IEEE, 2024: 194−199, articleTitle=null, refAbstract=null), Reference(id=1325490124296958334, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=88, rfOrder=93, authorNames=null, journalName=null, refType=null, unstructuredReference=Liu N F, Lin K, Hewitt J, et al. Lost in the middle: How language models use long contexts[J]. Transactions of the Association for Computational Linguistics, 2024, 12: 157−173, articleTitle=null, refAbstract=null), Reference(id=1325490124796080511, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=89, rfOrder=94, authorNames=null, journalName=null, refType=null, unstructuredReference=Rateike M, Cintas C, Wamburu J, et al. Weakly supervised detection of hallucinations in LLM activations[C]//Proc of the 36th Advances in Neural Information Processing Systems. Cambridge, MA: MIT, 2023: 1877−1901, articleTitle=null, refAbstract=null), Reference(id=1325490127706927488, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=90, rfOrder=95, authorNames=null, journalName=null, refType=null, unstructuredReference=Tenney I, Das D, Pavlick E. BERT rediscovers the classical NLP pipeline[C]//Proc of the 57th Annual Meeting of the Association for Computational Linguistics. Stroudsburg, PA: ACL, 2019: 4593−4601, articleTitle=null, refAbstract=null), Reference(id=1325490128537399681, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=91, rfOrder=96, authorNames=null, journalName=null, refType=null, unstructuredReference=Chuang Y S, Xie Yujia, Luo Hongyin, et al. DoLa: Decoding by contrasting layers improves factuality in large language models. [EB/OL]. (2024-01-16)[2024-12-21]. https://openreview.net/forum?id=Th6NyL07na, articleTitle=null, refAbstract=null), Reference(id=1325490129749553538, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=92, rfOrder=97, authorNames=null, journalName=null, refType=null, unstructuredReference=Varshney N, Yao Wenlin, Zhang Hongming, et al. A stitch in time saves nine: Detecting and mitigating hallucinations of LLMs by validating low-confidence generation[J]. arXiv preprint, arXiv: 2307.03987, 2023, articleTitle=null, refAbstract=null), Reference(id=1325490130584220035, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=93, rfOrder=98, authorNames=null, journalName=null, refType=null, unstructuredReference=Chen Kedi, Chen Qin, Zhou Jie, et al. Enhancing uncertainty modeling with semantic graph for hallucination detection[C]//Proc of the 39th AAAI Conf on Artificial Intelligence. Palo Alto, CA: AAAI, 2025: 23586−23594, articleTitle=null, refAbstract=null), Reference(id=1325490132261941636, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=94, rfOrder=99, authorNames=null, journalName=null, refType=null, unstructuredReference=Fu Jinlan, Ng S K, Jiang Zhengbao, et al. Gptscore: Evaluate as you desire[C]//Proc of the 2024 Conf of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). Stroudsburg, PA: ACL 2024: 6556−6576, articleTitle=null, refAbstract=null), Reference(id=1325490132756869509, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=95, rfOrder=100, authorNames=null, journalName=null, refType=null, unstructuredReference=Guerreiro N M, Voita E, Martins A F. Looking for a needle in a haystack: A comprehensive study of hallucinations in neural machine translation[C]//Proc of the 17th Conf of the European Chapter of the Association for Computational Linguistics. Stroudsburg, PA: ACL, 2023: 1059−1075, articleTitle=null, refAbstract=null), Reference(id=1325490134031937926, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=96, rfOrder=101, authorNames=null, journalName=null, refType=null, unstructuredReference=Yuan Weizhe, Neubig G, Liu Pengfei. Bartscore: Evaluating generated text as text generation[C]//Proc of the 34th Int Conf on Neural Information Processing Systems. New York: Curran Associates, 2021: 27263−27277, articleTitle=null, refAbstract=null), Reference(id=1325490136124895623, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=97, rfOrder=102, authorNames=null, journalName=null, refType=null, unstructuredReference=Xiao Yijun, Wang W Y. On hallucination and predictive uncertainty in conditional language generation[C]//Proc of the 16th Conf of the European Chapter of the Association for Computational Linguistics. Stroudsburg, PA: ACL, 2021: 2734−2744, articleTitle=null, refAbstract=null), Reference(id=1325490137349632392, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=98, rfOrder=103, authorNames=null, journalName=null, refType=null, unstructuredReference=Su Weihang, Tang Yichen, Ai Qingyao, et al. Mitigating entity-level hallucination in large language models[C]//Proc of the 2024 Annual Int ACM SIGIR Conf on Research and Development in Information Retrieval in the Asia Pacific Region. New York: ACM, 2024: 23−31, articleTitle=null, refAbstract=null), Reference(id=1325490138561786249, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=99, rfOrder=104, authorNames=null, journalName=null, refType=null, unstructuredReference=Van Der Poel L, Cotterell R, Meister C. Mutual information alleviates hallucinations in abstractive summarization[C]//Proc of the 2022 Conf on Empirical Methods in Natural Language Processing. Stroudsburg, PA: ACL, 2022: 5956−5965, articleTitle=null, refAbstract=null), Reference(id=1325490140709269898, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=100, rfOrder=105, authorNames=null, journalName=null, refType=null, unstructuredReference=Chuang Y S, Qiu Linlu, Hsieh C Y, et al. Lookback lens: Detecting and mitigating contextual hallucinations in large language models using only attention maps[C]//Proc of the 2024 Conf on Empirical Methods in Natural Language Processing. Stroudsburg, PA: ACL, 2024: 1419−1436, articleTitle=null, refAbstract=null), Reference(id=1325490141535547787, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=101, rfOrder=106, authorNames=null, journalName=null, refType=null, unstructuredReference=Sriramanan G, Bharti S, Sadasivan V S, et al. LLM-check: Investigating detection of hallucinations in large language models[C]//Proc of the 37th Int Conf on Neural Information Processing Systems. New York: Curran Associates, 2024: 34188−34216, articleTitle=null, refAbstract=null), Reference(id=1325490142345048461, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=102, rfOrder=107, authorNames=null, journalName=null, refType=null, unstructuredReference=Zablocki P, Gajewska Z. Assessing hallucination risks in large language models through internal state analysis[EB/OL]. (2024-07-17)[2025-07-11]. https://www.authorea.com/doi/full/10.22541/au.172124175.55788724, articleTitle=null, refAbstract=null), Reference(id=1325490142835782031, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=103, rfOrder=108, authorNames=null, journalName=null, refType=null, unstructuredReference=Hu Xiaomeng, Zhang Yiming, Peng Ru, et al. Embedding and gradient say wrong: A white-box method for hallucination detection[C]//Proc of the 2024 Conf on Empirical Methods in Natural Language Processing. Stroudsburg, PA: ACL, 2024, 1950−1959, articleTitle=null, refAbstract=null), Reference(id=1325490145264284048, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=104, rfOrder=109, authorNames=null, journalName=null, refType=null, unstructuredReference=Snyder B, Moisescu M, Zafar M B. On early detection of hallucinations in factual question answering[C]//Proc of the 30th ACM SIGKDD Conf on Knowledge Discovery and Data Mining. New York: ACM, 2024: 2721−2732, articleTitle=null, refAbstract=null), Reference(id=1325490145352364433, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=105, rfOrder=110, authorNames=null, journalName=null, refType=null, unstructuredReference=Sun Zhongxiang, Zang Xiaoxue, Zheng Kai, et al. ReDeEP: Detecting hallucination in retrieval-augmented generation via mechanistic interpretability[J]. arXiv preprint, arXiv: 2410.11414, 2024, articleTitle=null, refAbstract=null), Reference(id=1325490146111533458, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=106, rfOrder=111, authorNames=null, journalName=null, refType=null, unstructuredReference=Team G, Anil R, Borgeaud S, et al. Gemini: A family of highly capable multimodal models[J]. arXiv preprint, arXiv: 2312.11805, 2023, articleTitle=null, refAbstract=null), Reference(id=1325490146568712595, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=107, rfOrder=112, authorNames=null, journalName=null, refType=null, unstructuredReference=Bhamidipati P, Malladi A, Shrivastava M, et al. Zero-shot multi-task hallucination detection[J]. arXiv preprint, arXiv: 2403.12244, 2024, articleTitle=null, refAbstract=null), Reference(id=1325490146979754390, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=108, rfOrder=113, authorNames=null, journalName=null, refType=null, unstructuredReference=Rashad M, Zahran A, Amin A, et al. FactAlign: Fact-level hallucination detection and classification through knowledge graph alignment[C]//Proc of the 4th Workshop on Trustworthy Natural Language Processing. Stroudsburg, PA: ACL, 2024, 79−84, articleTitle=null, refAbstract=null), Reference(id=1325490148204491159, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=109, rfOrder=114, authorNames=null, journalName=null, refType=null, unstructuredReference=Sansford H, Richardson N, Maretic H P, et al. GraphEval: A knowledge-graph based LLM hallucination evaluation framework[J]. arXiv preprint, arXiv: 2407.10793, 2024, articleTitle=null, refAbstract=null), Reference(id=1325490149538279832, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=110, rfOrder=115, authorNames=null, journalName=null, refType=null, unstructuredReference=Durmus E, He H, Diab M. FEQA: A question answering evaluation framework for faithfulness assessment in abstractive summarization[C]//Proc of the 58th Annual Meeting of the Association for Computational Linguistics. Stroudsburg, PA: ACL, 2020: 5055−5070, articleTitle=null, refAbstract=null), Reference(id=1325490150335197593, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=111, rfOrder=116, authorNames=null, journalName=null, refType=null, unstructuredReference=Farquhar S, Kossen J, Kuhn L, et al. Detecting hallucinations in large language models using semantic entropy[J]. Nature, 2024, 630(8017): 625−630, articleTitle=null, refAbstract=null), Reference(id=1325490151585100186, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=112, rfOrder=117, authorNames=null, journalName=null, refType=null, unstructuredReference=Manakul P, Liusie A, Gales M J. Selfcheckgpt: Zero-resource black-box hallucination detection for generative large language models[C]//Proc of the 2023 Conf on Empirical Methods in Natural Language Processing. Stroudsburg, PA: ACL, 2023: 9004−9017, articleTitle=null, refAbstract=null), Reference(id=1325490154932154781, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=113, rfOrder=118, authorNames=null, journalName=null, refType=null, unstructuredReference=Fang Xinyue, Huang Zhen, Tian Zhiliang, et al. Zero-resource hallucination detection for text generation via graph-based contextual knowledge triples modeling[C]//Proc of the 39th AAAI Conf on Artificial Intelligence. Palo Alto, CA: AAAI, 2025: 23868−23877, articleTitle=null, refAbstract=null), Reference(id=1325490155397722526, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=114, rfOrder=119, authorNames=null, journalName=null, refType=null, unstructuredReference=Yang Shiping, Sun Renliang, Wan Xiaojun. A new benchmark and reverse validation method for passage-level hallucination detection[C]//Proc of the Findings of the Association for Computational Linguistics: EMNLP 2023. Stroudsburg, PA: ACL, 2023: 3898−3908, articleTitle=null, refAbstract=null), Reference(id=1325490156601487775, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=115, rfOrder=120, authorNames=null, journalName=null, refType=null, unstructuredReference=Honovich O, Choshen L, Aharoni R, et al. Evaluating factual consistency in knowledge-grounded dialogues via question generation and question answering[C]//Proc of the 2023 Conf on Empirical Methods in Natural Language Processing. Stroudsburg, PA: ACL, 2021: 7856−7870, articleTitle=null, refAbstract=null), Reference(id=1325490159105487264, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=116, rfOrder=121, authorNames=null, journalName=null, refType=null, unstructuredReference=Scialom T, Dray P A, Gallinari P, et al. QuestEval: Summarization asks for fact-based evaluation[C]//Proc of the 2021 Conf on Empirical Methods in Natural Language Processing. Stroudsburg, PA: ACL, 2021: 6594−6604, articleTitle=null, refAbstract=null), Reference(id=1325490159621386657, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=117, rfOrder=122, authorNames=null, journalName=null, refType=null, unstructuredReference=Wang A, Cho K, Lewis M. Asking and answering questions to evaluate the factual consistency of summaries[C]//Proc of the 58th Annual Meeting of the Association for Computational Linguistics. Stroudsburg, PA: ACL, 2020: 5008−5020, articleTitle=null, refAbstract=null), Reference(id=1325490160799986082, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=118, rfOrder=123, authorNames=null, journalName=null, refType=null, unstructuredReference=Fabbri A R, Wu C S, Liu Wenhao, et al. QAFactEval: Improved QA-based factual consistency evaluation for summarization[C]//Proc of the 2022 Conf of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Stroudsburg, PA: ACL, 2022: 2587−2601, articleTitle=null, refAbstract=null), Reference(id=1325490161265553827, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=119, rfOrder=124, authorNames=null, journalName=null, refType=null, unstructuredReference=Yehuda Y, Malkiel I, Barkan O, et al. InterrogateLLM: Zero-resource hallucination detection in LLM-generated answers[C]//Proc of the 62nd Annual Meeting of the Association for Computational Linguistics. Stroudsburg, PA: ACL, 2024: 9333−9347, articleTitle=null, refAbstract=null), Reference(id=1325490163392065956, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=120, rfOrder=125, authorNames=null, journalName=null, refType=null, unstructuredReference=Cohen R, Hamri M, Geva M, et al. LM vs LM: Detecting factual errors via cross examination[C]//Proc of the 2023 Conf on Empirical Methods in Natural Language Processing. Stroudsburg, PA: ACL, 2023: 12621−12640, articleTitle=null, refAbstract=null), Reference(id=1325490164180595109, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=121, rfOrder=126, authorNames=null, journalName=null, refType=null, unstructuredReference=Chiang C H, Lee H. Can large language models be an alternative to human evaluations?[C]//Proc of the 61st Annual Meeting of the Association for Computational Linguistics. Stroudsburg, PA: ACL, 2023: 15607−15631, articleTitle=null, refAbstract=null), Reference(id=1325490165061398950, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=122, rfOrder=127, authorNames=null, journalName=null, refType=null, unstructuredReference=Liu Yang, Iter D, Xu Yichong, et al. G-EVAL: NLG evaluation using GPT-4 with better human alignment[J]. arXiv preprint, arXiv: 2303.16634, 2023, articleTitle=null, refAbstract=null), Reference(id=1325490165430497703, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=123, rfOrder=128, authorNames=null, journalName=null, refType=null, unstructuredReference=Adlakha V, BehnamGhader P, Lu Xinghan, et al. Evaluating correctness and faithfulness of instruction-following models for question answering[J]. Transactions of the Association for Computational Linguistics, 2024, 12: 775−793, articleTitle=null, refAbstract=null), Reference(id=1325490165879288232, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=124, rfOrder=129, authorNames=null, journalName=null, refType=null, unstructuredReference=Gao Mingqi, Ruan Jie, Sun Renliang. Human-like summarization evaluation with ChatGPT[J]. arXiv preprint, arXiv: 2304.02554, 2023, articleTitle=null, refAbstract=null), Reference(id=1325490167548621225, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=125, rfOrder=130, authorNames=null, journalName=null, refType=null, unstructuredReference=Jain S, Keshava V, Sathyendra S M, et al. Multi-dimensional evaluation of text summarization with in-context learning[C]//Proc of the 61st Annual Meeting of the Association for Computational Linguistics. Stroudsburg, PA: ACL, 2023: 8487−8495, articleTitle=null, refAbstract=null), Reference(id=1325490167976440234, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=126, rfOrder=131, authorNames=null, journalName=null, refType=null, unstructuredReference=Luo Zheheng, Xie Qianqian, Ananiadou S. ChatGPT as a factual inconsistency evaluator for text summarization[J]. arXiv preprint, arXiv: 2303.15621, 2023, articleTitle=null, refAbstract=null), Reference(id=1325490169251508651, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=127, rfOrder=132, authorNames=null, journalName=null, refType=null, unstructuredReference=Dhuliawala S, Komeili M, Xu Jing, et al. Chain-of-verification reduces hallucination in large language models [C] //Findings of the Association for Computational Linguistics. Stroudsburg, PA: ACL, 2024: 3563−3578, articleTitle=null, refAbstract=null), Reference(id=1325490171751313836, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=128, rfOrder=133, authorNames=null, journalName=null, refType=null, unstructuredReference=Luo Jianjun, Xiao Cong, Ma Feng. Zero-resource hallucination prevention for large language models[J]. arXiv preprint, arXiv: 2309.02654, 2023, articleTitle=null, refAbstract=null), Reference(id=1325490172137189805, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=129, rfOrder=134, authorNames=null, journalName=null, refType=null, unstructuredReference=Agrawal A, Mirac S, Lester M, et al. Do language models know when they’re hallucinating references[J]. arXiv preprint, arXiv: 2305.18248, 2023, articleTitle=null, refAbstract=null), Reference(id=1325490172577591726, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=130, rfOrder=135, authorNames=null, journalName=null, refType=null, unstructuredReference=Das S, Srihari R K. Compos mentis at semeval2024 task6: A multi-faceted role-based large language model ensemble to detect hallucination[C]//Proc of the 18th Int Workshop on Semantic Evaluation (SemEval-2024). Stroudsburg, PA: ACL, 2024: 1449−1454, articleTitle=null, refAbstract=null), Reference(id=1325490172988633519, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=131, rfOrder=136, authorNames=null, journalName=null, refType=null, unstructuredReference=Zheng D, Lapata M, Pan J Z. Large language models as reliable knowledge bases?[J]. arXiv preprint, arXiv: 2407.13578, 2024, articleTitle=null, refAbstract=null), Reference(id=1325490174213370288, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=132, rfOrder=137, authorNames=null, journalName=null, refType=null, unstructuredReference=Son S S, Park J, Hwang J I, et al. HaRiM+: Evaluating summary quality with hallucination risk[J]. arXiv preprint, arXiv: 2211.12118, 2022, articleTitle=null, refAbstract=null), Reference(id=1325490174678938034, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=133, rfOrder=138, authorNames=null, journalName=null, refType=null, unstructuredReference=Min S, Krishna K, Lyu X, et al. FActScore: Fine-grained atomic evaluation of factual precision in long form text generation[C]//Proc of the 2023 Conf on Empirical Methods in Natural Language Processing. Stroudsburg, PA: ACL, 2023: 12076−12100, articleTitle=null, refAbstract=null), Reference(id=1325490176365048243, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=134, rfOrder=139, authorNames=null, journalName=null, refType=null, unstructuredReference=Chern I, Chern S, Chen Shiqi, et al. FacTool: Factuality detection in generative AI―A tool augmented framework for multi-task and multi-domain scenarios[J]. arXiv preprint, arXiv: 2307.13528, 2023, articleTitle=null, refAbstract=null), Reference(id=1325490177212297652, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=135, rfOrder=140, authorNames=null, journalName=null, refType=null, unstructuredReference=Hu Xiangkun, Ru Dongyu, Qiu Lin, et al. Knowledge-centric hallucination detection[C]//Proc of the 2024 Conf on Empirical Methods in Natural Language Processing. Stroudsburg, PA: ACL, 2024: 6953−6975, articleTitle=null, refAbstract=null), Reference(id=1325490178042769845, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=136, rfOrder=141, authorNames=null, journalName=null, refType=null, unstructuredReference=Mishra A, Asai A, Balachandran V, et al. Fine-grained hallucination detection and editing for language models[J]. arXiv preprint, arXiv: 2401.06855, 2024, articleTitle=null, refAbstract=null), Reference(id=1325490178927767990, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=137, rfOrder=142, authorNames=null, journalName=null, refType=null, unstructuredReference=Li Ningke, Li Yuekang, Liu Yi, et al. Drowzee: Metamorphic testing for fact-conflicting hallucination detection in large language models[C]//Proc of the ACM on Programming Languages. New York: ACM, 2024: 1843−1872, articleTitle=null, refAbstract=null), Reference(id=1325490180945228215, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=138, rfOrder=143, authorNames=null, journalName=null, refType=null, unstructuredReference=Bayat F F, Qian Kun, Han Benjamin, et al. Fleek: Factual error detection and correction with evidence retrieved from external knowledge[C]//Proc of the 2023 Conf on Empirical Methods in Natural Language Processing. Stroudsburg, PA: ACL, 2023: 124−130, articleTitle=null, refAbstract=null), Reference(id=1325490181381435832, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=139, rfOrder=144, authorNames=null, journalName=null, refType=null, unstructuredReference=Wang Binjie, Chern S, Chern E, et al. Halu-J: Critique-based hallucination judge[J]. arXiv preprint, arXiv: 2407.12943, 2024, articleTitle=null, refAbstract=null), Reference(id=1325490182186742202, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=140, rfOrder=145, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhao Xinping, Yu Jindi, Liu Zhenyu, et al. Medico: Towards hallucination detection and correction with multi-source evidence fusion[C]//Proc of the 2024 Conf on Empirical Methods in Natural Language Processing. Stroudsburg, PA: ACL, 2024: 34−45, articleTitle=null, refAbstract=null), Reference(id=1325490183038185915, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=141, rfOrder=146, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhang Jiawei, Xu Chejian, Gai Yu, et al. KnowHalu: Hallucination detection via multi-form knowledge based factual checking[J]. arXiv preprint, arXiv: 2404.02935, 2024, articleTitle=null, refAbstract=null), Reference(id=1325490185189863869, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=142, rfOrder=147, authorNames=null, journalName=null, refType=null, unstructuredReference=Wang Xiaohua, Yan Yuliang, Huang Longtao, et al. Hallucination detection for generative large language models by Bayesian sequential estimation[C]//Proc of the 2023 Conf on Empirical Methods in Natural Language Processing. Stroudsburg, PA: ACL, 2023: 15361−15371, articleTitle=null, refAbstract=null), Reference(id=1325490185978393023, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=143, rfOrder=148, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhou Chunting, Neubig G, Gu Jiatao, et al. Detecting hallucinated content in conditional neural sequence generation[J]. arXiv preprint, arXiv: 2011.02593, 2020, articleTitle=null, refAbstract=null), Reference(id=1325490186431377857, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=144, rfOrder=149, authorNames=null, journalName=null, refType=null, unstructuredReference=Wojciech K, McCann B, Xiong Caiming, et al. Evaluating the factual consistency of abstractive text summarization[C]//Proc of the 2023 Conf on Empirical Methods in Natural Language Processing. Stroudsburg, PA: ACL, 2023: 9332−9346, articleTitle=null, refAbstract=null), Reference(id=1325490187249267138, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=145, rfOrder=150, authorNames=null, journalName=null, refType=null, unstructuredReference=Qiu Yifu, Ziser Y, Korhonen A, et al. Detecting and mitigating hallucinations in multilingual summarisation[C]//Proc of the 2023 Conf on Empirical Methods in Natural Language Processing. Stroudsburg, PA: ACL, 2023: 8914−8932, articleTitle=null, refAbstract=null), Reference(id=1325490187723223491, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=146, rfOrder=151, authorNames=null, journalName=null, refType=null, unstructuredReference=Du Xuefeng, Xiao Chaowei, Li Yixuan. HaloScope: Harnessing unlabeled LLM generations for hallucination detection[J]. arXiv preprint, arXiv: 2409.17504, 2024, articleTitle=null, refAbstract=null), Reference(id=1325490189770043844, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=147, rfOrder=152, authorNames=null, journalName=null, refType=null, unstructuredReference=Quevedo E, Yero J, Koerner R, et al. Detecting hallucinations in large language model generation: A token probability approach[J]. arXiv preprint, arXiv: 2405.19648, 2024, articleTitle=null, refAbstract=null), Reference(id=1325490192261460421, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=148, rfOrder=153, authorNames=null, journalName=null, refType=null, unstructuredReference=Cao Meng, Dong Yue, Cheung J C K. Hallucinated but factual! Inspecting the factuality of hallucinations in abstractive summarization[C]//Proc of the 60th Annual Meeting of the Association for Computational Linguistics. Stroudsburg, PA: ACL, 2022: 3340−3354, articleTitle=null, refAbstract=null), Reference(id=1325490194782237128, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=149, rfOrder=154, authorNames=null, journalName=null, refType=null, unstructuredReference=Santhanam S, Hedayatnia B, Gella S, et al. Rome was built in 1776: A case study on factual correctness in knowledge-grounded response generation[J] arXiv preprint, arXiv: 2110.05456, 2021, articleTitle=null, refAbstract=null), Reference(id=1325490196166357449, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=150, rfOrder=155, authorNames=null, journalName=null, refType=null, unstructuredReference=Zha Yuheng, Yang Yichi, Li Ruichen, et al. AlignScore: Evaluating factual consistency with a unified alignment function[C]//Proc of the 61st Annual Meeting of the Association for Computational Linguistics. Stroudsburg, PA: ACL, 2023: 11328−11348, articleTitle=null, refAbstract=null), Reference(id=1325490198594859466, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=151, rfOrder=156, authorNames=null, journalName=null, refType=null, unstructuredReference=Shen Jiaming, Liu Jialu, Finnie D, et al. “Why is this misleading?”: Detecting news headline hallucinations with explanations[C]//Proc of the ACM Web Conf. New York: ACM, 2023: 1662−1672, articleTitle=null, refAbstract=null), Reference(id=1325490200280969676, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=152, rfOrder=157, authorNames=null, journalName=null, refType=null, unstructuredReference=Choi S, Fang Tianqing, Wang Zhaowei, et al. KCTS: Knowledge-constrained tree search decoding with token-level hallucination detection[C]//Proc of the 2023 Conf on Empirical Methods in Natural Language Processing. Stroudsburg, PA: ACL, 2023: 14035−14053, articleTitle=null, refAbstract=null), Reference(id=1325490201115636173, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=153, rfOrder=158, authorNames=null, journalName=null, refType=null, unstructuredReference=Qiu Yifu, Embar V, Shay B, et al. Think while you write: Hypothesis verification promotes faithful knowledge-to-text generation[C]//Proc of the Findings of the Association for Computational Linguistics: NAACL 2024. Stroudsburg, PA: ACL, 2023: 1628−1644, articleTitle=null, refAbstract=null), Reference(id=1325490203183428046, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=154, rfOrder=159, authorNames=null, journalName=null, refType=null, unstructuredReference=Himmi A, Staerman G, Picot M, et al. Enhanced hallucination detection in neural machine translation through simple detector aggregation[J]. arXiv preprint, arXiv: 2402.13331, 2024, articleTitle=null, refAbstract=null), Reference(id=1325490206106857935, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=155, rfOrder=160, authorNames=null, journalName=null, refType=null, unstructuredReference=Su Weihang, Wang Changyue, Ai Qingyao, et al. Unsupervised real-time hallucination detection based on the internal states of large language models[J]. arXiv preprint, arXiv: 2403.06448, 2024, articleTitle=null, refAbstract=null), Reference(id=1325490208694743504, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=156, rfOrder=161, authorNames=null, journalName=null, refType=null, unstructuredReference=Lin S, Hilton J, Evans O. TruthfulQA: Measuring how models mimic human falsehoods[C]//Proc of the 60th Annual Meeting of the Association for Computational Linguistics. Stroudsburg, PA: ACL, 2022: 3214−3252, articleTitle=null, refAbstract=null), Reference(id=1325490213283312081, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=157, rfOrder=162, authorNames=null, journalName=null, refType=null, unstructuredReference=Liu Tianyu, Zhang Yizhe, Brockett C, et al. A token-level reference-free hallucination detection benchmark for free-form text generation[C]//Proc of the 60th Annual Meeting of the Association for Computational Linguistics. Stroudsburg, PA: ACL, 2022: 6723−6737, articleTitle=null, refAbstract=null), Reference(id=1325490214503854546, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=158, rfOrder=163, authorNames=null, journalName=null, refType=null, unstructuredReference=Liang Xun, Song Shichao, Niu Simin, et al. UHGEval: Benchmarking the hallucination of Chinese large language models via unconstrained generation[J]. arXiv preprint, arXiv: 2311.15296, 2023, articleTitle=null, refAbstract=null), Reference(id=1325490219096617429, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=159, rfOrder=164, authorNames=null, journalName=null, refType=null, unstructuredReference=Dale D, Voita E, Lam J, et al. HalOmi: A manually annotated benchmark for multilingual hallucination and omission detection in machine translation[J]. arXiv preprint, arXiv: 2305.11746, 2023, articleTitle=null, refAbstract=null), Reference(id=1325490221202158038, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=160, rfOrder=165, authorNames=null, journalName=null, refType=null, unstructuredReference=Hu Xiangkun, Ru Dongyu, Qiu Lin. RefChecker: Reference-based fine-grained hallucination checker and benchmark for large language models[J]. arXiv preprint, arXiv: 2405.14486, 2024, articleTitle=null, refAbstract=null), Reference(id=1325490222045213143, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=161, rfOrder=166, authorNames=null, journalName=null, refType=null, unstructuredReference=Chen Kedi, Chen Qin, Zhou Jie, et al. DiaHalu: A dialogue-level hallucination evaluation benchmark for large language models[J]. arXiv preprint, arXiv: 2403.00896, 2024, articleTitle=null, refAbstract=null), Reference(id=1325490222485615064, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=162, rfOrder=167, authorNames=null, journalName=null, refType=null, unstructuredReference=Luo Wen, Shen Tianshu, Li Wei, et al. HalluDial: A large-scale benchmark for automatic dialogue-level hallucination evaluation[J]. arXiv preprint, arXiv: 2406.07070, 2024, articleTitle=null, refAbstract=null), Reference(id=1325490222972154329, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=163, rfOrder=168, authorNames=null, journalName=null, refType=null, unstructuredReference=Ravi S S, Mielczarek B, Kannappan A, et al. Lynx: An open source hallucination evaluation model[J]. arXiv preprint arXiv: 2407.08488, 2024, articleTitle=null, refAbstract=null), Reference(id=1325490223752294874, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=164, rfOrder=169, authorNames=null, journalName=null, refType=null, unstructuredReference=Cheng, Qinyuan, Sun Tianxiang, Zhang Wenwei, et al. Evaluating hallucinations in Chinese large language models[J]. arXiv preprint, arXiv: 2310.03368, 2023, articleTitle=null, refAbstract=null), Reference(id=1325490224175919579, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=165, rfOrder=170, authorNames=null, journalName=null, refType=null, unstructuredReference=Dale D, Costa-jussà M. Blaser 2.0: A metric for evaluation and quality estimation of massively multilingual speech and text translation[C]//Proc of the 2024 Conf on Empirical Methods in Natural Language Processing. Stroudsburg, PA: ACL, 2024: 16075−16085, articleTitle=null, refAbstract=null), Reference(id=1325490225845252572, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=166, rfOrder=171, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhang Hanzhi, Anjum S, Fan Heng, et al. Poly-FEVER: A multilingual fact verification benchmark for hallucination detection in large language models[J]. arXiv preprint, arXiv: 2503.16541, 2025, articleTitle=null, refAbstract=null), Reference(id=1325490226277265885, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=167, rfOrder=172, authorNames=null, journalName=null, refType=null, unstructuredReference=Etxaniz J, Sainz O, Miguel N, et al. Latxa: An open language model and evaluation suite for Basque[C]//Proc of the 62nd Annual Meeting of the Association for Computational Linguistics. Stroudsburg, PA: ACL, 2024: 14952−14972, articleTitle=null, refAbstract=null), Reference(id=1325490226675724766, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=168, rfOrder=173, authorNames=null, journalName=null, refType=null, unstructuredReference=Li Junyi, Cheng Xiaoxue, Zhao Xin, et al. HaluEval: A large-scale hallucination evaluation benchmark for large language models[C]//Proc of the 2023 Conf on Empirical Methods in Natural Language Processing. Stroudsburg, PA: ACL, 2023: 6449−6464, articleTitle=null, refAbstract=null), Reference(id=1325490227527168480, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=169, rfOrder=174, authorNames=null, journalName=null, refType=null, unstructuredReference=Cao Zouying, Yang Yifei, Zhao Hai. AutoHall: Automated hallucination dataset generation for large language models[J]. arXiv preprint, arXiv: 2310.00259, 2023, articleTitle=null, refAbstract=null), Reference(id=1325490228336669153, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=170, rfOrder=175, authorNames=null, journalName=null, refType=null, unstructuredReference=Ravichander A, Ghela S, Wadden D, et al. The HALoGen benchmark: Fantastic LLM hallucinations and where to find Them[EB/OL]. (2024-10-15)[2024-12-30]. https://openreview.net/pdf?id=pQ9QDzckB7, articleTitle=null, refAbstract=null), Reference(id=1325490230085693922, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=171, rfOrder=176, authorNames=null, journalName=null, refType=null, unstructuredReference=Chen Xiang, Song Duanzheng, Gui Honghao, et al. Factchd: Benchmarking fact-conflicting hallucination detection[C]//Proc of the 33rd Int Joint Conf on Artificial Intelligence. San Mateo, CA: Morgan Kaufmann, 2024: 6216−6224, articleTitle=null, refAbstract=null), Reference(id=1325490230861640163, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=172, rfOrder=177, authorNames=null, journalName=null, refType=null, unstructuredReference=Bao F S, Li M, Qu Renyi, et al. FaithBench: A diverse hallucination benchmark for summarization by modern LLMs[J]. arXiv preprint, arXiv: 2410.13210, 2024, articleTitle=null, refAbstract=null), Reference(id=1325490231306236388, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=173, rfOrder=178, authorNames=null, journalName=null, refType=null, unstructuredReference=Li Junyi, Chen Jie, Ren Ruiyang, et al. The dawn after the dark: An empirical study on factuality hallucination in large language models[J]. arXiv preprint, arXiv: 2401.03205, 2024, articleTitle=null, refAbstract=null), Reference(id=1325490231759221221, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=174, rfOrder=179, authorNames=null, journalName=null, refType=null, unstructuredReference=Chen Shiqi, Zhao Yiran, Zhang Jinghan, et al. Felm: Benchmarking factuality evaluation of large language models[C]//Proc of the 37th Int Conf on Neural Information Processing Systems. New York: Curran Associates, 2024: 44502−44523, articleTitle=null, refAbstract=null), Reference(id=1325490232518390246, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=175, rfOrder=180, authorNames=null, journalName=null, refType=null, unstructuredReference=Kasai J, Sakaguchi K, Takahashi Y, et al. REALTIME QA: What’s the answer right now?[C]//Proc of the 37th Int Conf on Neural Information Processing Systems. New York: Curran Associates, 2024: 49025−49043, articleTitle=null, refAbstract=null), Reference(id=1325490233411777000, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=176, rfOrder=181, authorNames=null, journalName=null, refType=null, unstructuredReference=Muhlgay D, Ram O, Magar I, et al. Generating benchmarks for factuality evaluation of language models[C]//Proc of the 18th Conf of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers). Stroudsburg, PA: ACL 2024: 49−66, articleTitle=null, refAbstract=null), Reference(id=1325490234640708073, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=177, rfOrder=182, authorNames=null, journalName=null, refType=null, unstructuredReference=Dong Zican, Tang Tianyi, Li Junyi, et al. Bamboo: A comprehensive benchmark for evaluating long text modeling capacities of large language models[J]. arXiv preprint, arXiv: 2309.13345, 2023, articleTitle=null, refAbstract=null)], funds=null, companyList=[AuthorCompany(id=1325489965806792865, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, xref=1, ext=[AuthorCompanyExt(id=1325489965857124514, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, companyId=1325489965806792865, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1College of Systems Engineering, National University of Defense Technology, Changsha 410073), AuthorCompanyExt(id=1325489965882290339, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, companyId=1325489965806792865, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1国防科技大学系统工程学院 长沙 410073)]), AuthorCompany(id=1325489966649847972, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, xref=2, ext=[AuthorCompanyExt(id=1325489967006363813, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, companyId=1325489966649847972, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
2College of Computer Science and Technology, National University of Defense Technology, Changsha 410073), AuthorCompanyExt(id=1325489967211884710, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, companyId=1325489966649847972, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
2国防科技大学计算机学院 长沙 410073)]), AuthorCompany(id=1325489967849418919, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, xref=3, ext=[AuthorCompanyExt(id=1325489967908139176, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, companyId=1325489967849418919, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
3National Key Laboratory of Parallel and Distributed Computing (National University of Defense Technology), Changsha 410073), AuthorCompanyExt(id=1325489967929110697, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, companyId=1325489967849418919, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
3并行与分布计算全国重点实验室(国防科技大学) 长沙 410073)])], figs=[ArticleFig(id=1325489990985199843, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, language=EN, label=Figure 1, caption=
Examples of hallucination in LLMs, figureFileSmall=9mvxw/ytakGJwTn4SaXL+w==, figureFileBig=GdNBukMMRfHY+lEQXLsblw==, tableContent=null), ArticleFig(id=1325489993019437284, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, language=CN, label=图1, caption=
大语言模型幻觉示例, figureFileSmall=9mvxw/ytakGJwTn4SaXL+w==, figureFileBig=GdNBukMMRfHY+lEQXLsblw==, tableContent=null), ArticleFig(id=1325489994290311397, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, language=EN, label=Figure 2, caption=
The cause of the large language model hallucination generation, figureFileSmall=FnMGLeyTNS6ejSaM9FcV7w==, figureFileBig=0J5GcqpdAGq/UGPVgu8L/g==, tableContent=null), ArticleFig(id=1325489995150143718, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, language=CN, label=图2, caption=
大语言模型幻觉产生的原因, figureFileSmall=FnMGLeyTNS6ejSaM9FcV7w==, figureFileBig=0J5GcqpdAGq/UGPVgu8L/g==, tableContent=null), ArticleFig(id=1325489996370686183, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, language=EN, label=Figure 3, caption=
Examples of composite hallucination in LLMs, figureFileSmall=xJ/W50jgbJn1WtFJpIBBCg==, figureFileBig=AhGP45gPmdT0Gk6BhqkY1g==, tableContent=null), ArticleFig(id=1325489997326987496, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, language=CN, label=图3, caption=
大语言模型复合幻觉示例, figureFileSmall=xJ/W50jgbJn1WtFJpIBBCg==, figureFileBig=AhGP45gPmdT0Gk6BhqkY1g==, tableContent=null), ArticleFig(id=1325489997738029289, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, language=EN, label=Figure 4, caption=
Hallucination detection framework for white-box models, figureFileSmall=gXP7JRgeh3F1ZnnkovAvkA==, figureFileBig=5YMrBy1B+jO0xVrMXvoyGw==, tableContent=null), ArticleFig(id=1325489998539141354, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, language=CN, label=图4, caption=
针对白盒模型的幻觉检测框架, figureFileSmall=gXP7JRgeh3F1ZnnkovAvkA==, figureFileBig=5YMrBy1B+jO0xVrMXvoyGw==, tableContent=null), ArticleFig(id=1325489998975348971, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, language=EN, label=Figure 5, caption=
Zero-resource hallucination detection framework for black-box models, figureFileSmall=D6iPfdithkpg7o3gRAvDgg==, figureFileBig=viuLtNVp9fNMfTu7cuS44Q==, tableContent=null), ArticleFig(id=1325489999541580012, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, language=CN, label=图5, caption=
针对黑盒模型的零资源幻觉检测框架, figureFileSmall=D6iPfdithkpg7o3gRAvDgg==, figureFileBig=viuLtNVp9fNMfTu7cuS44Q==, tableContent=null), ArticleFig(id=1325490000145559789, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, language=EN, label=Figure 6, caption=
Non-zero-resource hallucination detection framework for black-box models, figureFileSmall=Rn8JdiozlXA5/Ubioz9X4A==, figureFileBig=89ywh0OJF/wlicYySyavOw==, tableContent=null), ArticleFig(id=1325490001861030127, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, language=CN, label=图6, caption=
针对黑盒模型的非零资源幻觉检测框架, figureFileSmall=Rn8JdiozlXA5/Ubioz9X4A==, figureFileBig=89ywh0OJF/wlicYySyavOw==, tableContent=null), ArticleFig(id=1325490002301432048, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, language=EN, label=Figure 7, caption=
Citation count of literature corresponding to the hallucination detection benchmarks, figureFileSmall=I4a2K8qreQ6gkdaKDBkVrw==, figureFileBig=3C5r/E+EKUuFvyX0Hln6hw==, tableContent=null), ArticleFig(id=1325490003182235889, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, language=CN, label=图7, caption=
幻觉检测基准对应文献的引用次数, figureFileSmall=I4a2K8qreQ6gkdaKDBkVrw==, figureFileBig=3C5r/E+EKUuFvyX0Hln6hw==, tableContent=null), ArticleFig(id=1325490004008513778, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, language=EN, label=Table 1, caption=
Classification of Large Language Model Hallucination, figureFileSmall=null, figureFileBig=null, tableContent=
| 类型 | 划分维度 | 划分边界说明 |
|---|
| 语义忠诚性幻觉 | 输入忠诚度 | 输出偏离用户提问的核心意图或语义 |
| 事实一致性幻觉 | 知识准确度 | 错误的知识源于模型内部记忆 |
| 上下文一致性幻觉 | 输入忠诚度 | 输出未偏离用户语义,但内容存在 上下文对话历史矛盾或不连贯 |
| 外部依赖性幻觉 | 知识准确度 | 错误的知识源于外部检索知识库 |
), ArticleFig(id=1325490005245833459, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, language=CN, label=表1, caption=
大语言模型幻觉分类
, figureFileSmall=null, figureFileBig=null, tableContent=
| 类型 | 划分维度 | 划分边界说明 |
|---|
| 语义忠诚性幻觉 | 输入忠诚度 | 输出偏离用户提问的核心意图或语义 |
| 事实一致性幻觉 | 知识准确度 | 错误的知识源于模型内部记忆 |
| 上下文一致性幻觉 | 输入忠诚度 | 输出未偏离用户语义,但内容存在 上下文对话历史矛盾或不连贯 |
| 外部依赖性幻觉 | 知识准确度 | 错误的知识源于外部检索知识库 |
), ArticleFig(id=1325490006512513268, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, language=EN, label=Table 2, caption=
Analysis of the Hallucinations Causes, figureFileSmall=null, figureFileBig=null, tableContent=
| 模型能力 | ※ | ■ | * | ▲ | △ | ▼ | ▽ | ◆ | ◇ | ◎ | ○ | ★ | ☆ | ☉ | ● | ◢ |
|---|
| 注:第1行符号含义如图2所示,“×”表示诱因通过影响模型的该能力导致幻觉的产生。 |
| 拥有知识 | × | × | × | × | × | × | × | × | × | × | | | | | × | × |
| 理解问题 | × | × | × | | | | | | | | × | | | | | |
| 表达知识 | × | × | × | | | | | | | | × | × | × | × | | |
), ArticleFig(id=1325490007741444341, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, language=CN, label=表2, caption=
幻觉诱因分析
, figureFileSmall=null, figureFileBig=null, tableContent=
| 模型能力 | ※ | ■ | * | ▲ | △ | ▼ | ▽ | ◆ | ◇ | ◎ | ○ | ★ | ☆ | ☉ | ● | ◢ |
|---|
| 注:第1行符号含义如图2所示,“×”表示诱因通过影响模型的该能力导致幻觉的产生。 |
| 拥有知识 | × | × | × | × | × | × | × | × | × | × | | | | | × | × |
| 理解问题 | × | × | × | | | | | | | | × | | | | | |
| 表达知识 | × | × | × | | | | | | | | × | × | × | × | | |
), ArticleFig(id=1325490008538362102, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, language=EN, label=Table 3, caption=
Classification of Hallucination Detection Methods, figureFileSmall=null, figureFileBig=null, tableContent=
), ArticleFig(id=1325490010698428664, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, language=CN, label=表3, caption=
幻觉检测方法分类
, figureFileSmall=null, figureFileBig=null, tableContent=
), ArticleFig(id=1325490011474374905, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, language=EN, label=Table 4, caption=
Summary of Hallucination Detection Methods, figureFileSmall=null, figureFileBig=null, tableContent=
| 适用模型 | 分类 | 检测思路 | 检测原理 | 优点 | 不足 |
|---|
| 白盒模型 | 单特征 | 隐藏层激活值 | 利用模型内部的状态信息, 识别生成内容中的幻觉 | 捕捉深层语义变化, 细粒度检测能力强 | 计算开销较大、模型迁移性 与通用性较弱 |
| logits值 | 实现简单、计算效率高 | 难以捕获深层次语义不一致等问题 |
| 熵值 | 熵值可结合条件熵等衍生指标, 实现细粒度评估与动态调整 | 过于依赖概率分布的准确性 |
| 注意力权重 | 能显式衡量生成内容对输入上下文的依赖程度,可解释性较强 | 注意力机制自身偏差容易引起误判 |
| 梯度 | 细粒度反映输入特征对 输出的影响,检测灵敏 | 计算开销较大、模型迁移性 与通用性较弱 |
| 多特征 | | 结合模型内部状态的多种 特征进行幻觉检测 | 可利用信息丰富、检测精度较高 | 不同特征之间可能存在信息冗余 |
| 黑盒模型 | 零资源 | 传统方法迁移 | 将传统幻觉检测方法的思路 迁移至大语言模型上 | 技术简单、减少了重新 设计检测机制的成本 | 跨领域和跨任务的泛化能力较弱 |
| 生成多次响应 | 通过多次生成响应,分析样本一致性以评估生成内容的可靠性 | 无需额外的标注数据、简单 易实施、计算成本相对较低 | 随机采样本身带来的噪声可能影响分析结果,导致检测误差 |
| 反向验证 | 通过生成的答案重新构造查询,评估生成的查询与原始查询的一致性 | 无需外部知识库的支持, 具有较强的可靠性 | 反向验证过程中涉及高复杂度的语法或逻辑设计,同时容易产生误差 |
| 基于大模型 | 利用大语言模型的内部知识对生成的内容进行检测 | 避免依赖外部数据库或知识库,自动化程度高、易于实现、拓展性强 | 高度依赖于语言模型本身的推理能力和生成质量 |
| 非零资源 | 基于外部数据库 | 将生成内容与外部数据库进行比对验证,以识别生成内容中可能存在的幻觉 | 具有较高的准确性和可信度 | 受外部资源质量和计算条件的限制 |
| 基于分类器 | 构造合适的幻觉数据集对分类器进行训练,利用训练好的分类器进行幻觉检测 | 具有较高的检测精度和灵活 性,自动化检测程度高 | 数据集构造成本高,且分类器的泛化能力可能受到数据集覆盖范围的限制 |
), ArticleFig(id=1325490012321624314, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, language=CN, label=表4, caption=
幻觉检测方法总结
, figureFileSmall=null, figureFileBig=null, tableContent=
| 适用模型 | 分类 | 检测思路 | 检测原理 | 优点 | 不足 |
|---|
| 白盒模型 | 单特征 | 隐藏层激活值 | 利用模型内部的状态信息, 识别生成内容中的幻觉 | 捕捉深层语义变化, 细粒度检测能力强 | 计算开销较大、模型迁移性 与通用性较弱 |
| logits值 | 实现简单、计算效率高 | 难以捕获深层次语义不一致等问题 |
| 熵值 | 熵值可结合条件熵等衍生指标, 实现细粒度评估与动态调整 | 过于依赖概率分布的准确性 |
| 注意力权重 | 能显式衡量生成内容对输入上下文的依赖程度,可解释性较强 | 注意力机制自身偏差容易引起误判 |
| 梯度 | 细粒度反映输入特征对 输出的影响,检测灵敏 | 计算开销较大、模型迁移性 与通用性较弱 |
| 多特征 | | 结合模型内部状态的多种 特征进行幻觉检测 | 可利用信息丰富、检测精度较高 | 不同特征之间可能存在信息冗余 |
| 黑盒模型 | 零资源 | 传统方法迁移 | 将传统幻觉检测方法的思路 迁移至大语言模型上 | 技术简单、减少了重新 设计检测机制的成本 | 跨领域和跨任务的泛化能力较弱 |
| 生成多次响应 | 通过多次生成响应,分析样本一致性以评估生成内容的可靠性 | 无需额外的标注数据、简单 易实施、计算成本相对较低 | 随机采样本身带来的噪声可能影响分析结果,导致检测误差 |
| 反向验证 | 通过生成的答案重新构造查询,评估生成的查询与原始查询的一致性 | 无需外部知识库的支持, 具有较强的可靠性 | 反向验证过程中涉及高复杂度的语法或逻辑设计,同时容易产生误差 |
| 基于大模型 | 利用大语言模型的内部知识对生成的内容进行检测 | 避免依赖外部数据库或知识库,自动化程度高、易于实现、拓展性强 | 高度依赖于语言模型本身的推理能力和生成质量 |
| 非零资源 | 基于外部数据库 | 将生成内容与外部数据库进行比对验证,以识别生成内容中可能存在的幻觉 | 具有较高的准确性和可信度 | 受外部资源质量和计算条件的限制 |
| 基于分类器 | 构造合适的幻觉数据集对分类器进行训练,利用训练好的分类器进行幻觉检测 | 具有较高的检测精度和灵活 性,自动化检测程度高 | 数据集构造成本高,且分类器的泛化能力可能受到数据集覆盖范围的限制 |
), ArticleFig(id=1325490013210816763, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, language=EN, label=Table 5, caption=
Benchmark for Hallucination Detection in Large Language Models, figureFileSmall=null, figureFileBig=null, tableContent=
| 基准 | 类型 | 规模 | 细粒度 | 语言 | 幻觉种类 | 任务类型、(不限于) | 评价指标 |
|---|
| SFH | FCH | CCH | EDH |
|---|
| 注:SFH表示语义忠诚性幻觉,FCH表示事实一致性幻觉,CCH表示上下文一致性幻觉,EDH表示外部依赖性幻觉。 |
| TruthfulQA[156] | 幻觉评估 | 817 | 句子级别 | 英文 | | √ | | | 知识问答、 多项选择 | Acc |
| HaluEval[168] | 幻觉评估 | 35000 | 句子级别 | 英文 | √ | √ | √ | | 知识问答、 多轮对话、 摘要生成 | Acc |
| UHGEval[158] | 幻觉评估 | 5141 | 词元级别、 句子级别 | 中文 | | √ | | | 文本生成 | Acc, BLEU-4, ROUGE-L等 |
| HalluQA[164] | 幻觉评估 | 450 | 句子级别 | 中文 | | √ | | | 知识问答、 多轮对话 | Non-Hallucination Rate等 |
| AutoHall[169] | 幻觉检测 | 2844 | 句子级别 | 英文 | | √ | √ | | 知识问答、 摘要生成、 多轮对话 | Acc, F1 |
| DiaHalu[161] | 幻觉评估、 幻觉检测 | 1103 | 对话级别 | 英文 | √ | √ | | | 多轮对话 | Precission, Recall, F1 |
| FactCHD[170] | 幻觉评估 | 58343 | 句子级别 | 英文 | | √ | | | 知识问答、 多轮对话 | Micro F1, Expmatch |
| FaithBench[171] | 幻觉评估 | 660 | 句子级别 | 英文 | √ | √ | | | 摘要生成 | Micro F1, Balanced Accuracy |
| HALoGen[172] | 幻觉评估 | 150000 | 句子级别 | 英文 | √ | √ | | | 代码生成、 摘要生成、 科学引用 | Hallucination Score等 |
| HELM[155] | 幻觉检测 | 3342 | 句子级别、 段落级别 | 英文 | √ | √ | | | 知识问答、 摘要生成、 文本生成 | AUC, PCCs |
| HalOmi[159] | 幻觉检测 | <3546 | 词元级别、 句子级别 | 多语言 | √ | √ | | | 机器翻译 | AUC, AOC |
| HalluDial[162] | 幻觉评估 | 146856 | 对话级别 | 英文 | √ | √ | | | 知识问答 | Acc, Macro F1 |
| HaluBench[163] | 幻觉评估 | 15000 | 句子级别、 语义级别 | 英文 | | √ | √ | √ | 知识问答、 摘要生成 | Acc, Macro F1等 |
| HaluEval 2.0[173] | 幻觉评估 | 8770 | 句子级别、 段落级别 | 英文 | | √ | √ | | 知识问答、 摘要生成 | Micro hallucination rate等 |
| RefChecker[160] | 幻觉检测 | 11000 | 知识三元组级别 | 英文 | | √ | | √ | 知识问答、 摘要生成 | Acc, Macro F1 |
| HADES[157] | 幻觉检测 | 12719 | 词元级别 | 英文 | √ | √ | √ | | 知识问答、 多轮对话 | Precision, Recall, F1等 |
| PHD[114] | 幻觉检测 | 300 | 段落级别 | 英文 | | √ | | | 知识问答 | Acc, Precision, F1, Recall |
| FELM[174] | 幻觉检测 | 3948 | 句子级别、 段落级别 | 英文 | | √ | | | 多任务 | Precision, F1, Recall等 |
| REALTIMEQA[175] | 幻觉评估 | | 句子级别 | 英文 | | √ | | | 知识问答 | Acc, Exact Match, F1 |
| FACTOR[176] | 幻觉评估 | 4266 | 句子级别 | 英文 | | √ | | | 知识问答、 摘要生成 | Acc |
| BAMBOO[177] | 幻觉评估 | 3004 | 句子级别 | 英文 | | √ | √ | | 长文本生成 | Concordance Index, Acc, F1 |
| Poly-FEVER[25] | 幻觉检测 | 77973 | 句子级别 | 多语言 | | √ | | | 事实验证 | Acc |
| RAGTruth[71] | 幻觉评估 | 18000 | 句子级别、 段落级别 | 英文 | | | | √ | 知识问答、 摘要生成 | Precision, Recall, F1 |
), ArticleFig(id=1325490015316357373, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325489947351855231, language=CN, label=表5, caption=
大语言模型幻觉检测基准
, figureFileSmall=null, figureFileBig=null, tableContent=
| 基准 | 类型 | 规模 | 细粒度 | 语言 | 幻觉种类 | 任务类型、(不限于) | 评价指标 |
|---|
| SFH | FCH | CCH | EDH |
|---|
| 注:SFH表示语义忠诚性幻觉,FCH表示事实一致性幻觉,CCH表示上下文一致性幻觉,EDH表示外部依赖性幻觉。 |
| TruthfulQA[156] | 幻觉评估 | 817 | 句子级别 | 英文 | | √ | | | 知识问答、 多项选择 | Acc |
| HaluEval[168] | 幻觉评估 | 35000 | 句子级别 | 英文 | √ | √ | √ | | 知识问答、 多轮对话、 摘要生成 | Acc |
| UHGEval[158] | 幻觉评估 | 5141 | 词元级别、 句子级别 | 中文 | | √ | | | 文本生成 | Acc, BLEU-4, ROUGE-L等 |
| HalluQA[164] | 幻觉评估 | 450 | 句子级别 | 中文 | | √ | | | 知识问答、 多轮对话 | Non-Hallucination Rate等 |
| AutoHall[169] | 幻觉检测 | 2844 | 句子级别 | 英文 | | √ | √ | | 知识问答、 摘要生成、 多轮对话 | Acc, F1 |
| DiaHalu[161] | 幻觉评估、 幻觉检测 | 1103 | 对话级别 | 英文 | √ | √ | | | 多轮对话 | Precission, Recall, F1 |
| FactCHD[170] | 幻觉评估 | 58343 | 句子级别 | 英文 | | √ | | | 知识问答、 多轮对话 | Micro F1, Expmatch |
| FaithBench[171] | 幻觉评估 | 660 | 句子级别 | 英文 | √ | √ | | | 摘要生成 | Micro F1, Balanced Accuracy |
| HALoGen[172] | 幻觉评估 | 150000 | 句子级别 | 英文 | √ | √ | | | 代码生成、 摘要生成、 科学引用 | Hallucination Score等 |
| HELM[155] | 幻觉检测 | 3342 | 句子级别、 段落级别 | 英文 | √ | √ | | | 知识问答、 摘要生成、 文本生成 | AUC, PCCs |
| HalOmi[159] | 幻觉检测 | <3546 | 词元级别、 句子级别 | 多语言 | √ | √ | | | 机器翻译 | AUC, AOC |
| HalluDial[162] | 幻觉评估 | 146856 | 对话级别 | 英文 | √ | √ | | | 知识问答 | Acc, Macro F1 |
| HaluBench[163] | 幻觉评估 | 15000 | 句子级别、 语义级别 | 英文 | | √ | √ | √ | 知识问答、 摘要生成 | Acc, Macro F1等 |
| HaluEval 2.0[173] | 幻觉评估 | 8770 | 句子级别、 段落级别 | 英文 | | √ | √ | | 知识问答、 摘要生成 | Micro hallucination rate等 |
| RefChecker[160] | 幻觉检测 | 11000 | 知识三元组级别 | 英文 | | √ | | √ | 知识问答、 摘要生成 | Acc, Macro F1 |
| HADES[157] | 幻觉检测 | 12719 | 词元级别 | 英文 | √ | √ | √ | | 知识问答、 多轮对话 | Precision, Recall, F1等 |
| PHD[114] | 幻觉检测 | 300 | 段落级别 | 英文 | | √ | | | 知识问答 | Acc, Precision, F1, Recall |
| FELM[174] | 幻觉检测 | 3948 | 句子级别、 段落级别 | 英文 | | √ | | | 多任务 | Precision, F1, Recall等 |
| REALTIMEQA[175] | 幻觉评估 | | 句子级别 | 英文 | | √ | | | 知识问答 | Acc, Exact Match, F1 |
| FACTOR[176] | 幻觉评估 | 4266 | 句子级别 | 英文 | | √ | | | 知识问答、 摘要生成 | Acc |
| BAMBOO[177] | 幻觉评估 | 3004 | 句子级别 | 英文 | | √ | √ | | 长文本生成 | Concordance Index, Acc, F1 |
| Poly-FEVER[25] | 幻觉检测 | 77973 | 句子级别 | 多语言 | | √ | | | 事实验证 | Acc |
| RAGTruth[71] | 幻觉评估 | 18000 | 句子级别、 段落级别 | 英文 | | | | √ | 知识问答、 摘要生成 | Precision, Recall, F1 |
)], attaches=null, journal=Journal(id=1324759606947315908, delFlag=0, nameCn=计算机研究与发展, nameEn=Journal of Computer Research and Development, nameHistory1=null, nameHistory2=null, issn=1000-1239, eissn=null, cn=11-1777/TP, coden=null, periodic=0, language=CN, oaType=null, ccby=null, superviseOffice=null, ownerOffice=null, pubOffice=null, editorOffice=null, officeType=null, aims=null, clcCode=null, officeProv=null, officeCity=null, officeAddr=null, officeZip=null, officeEmail=null, officePhone=null, editDirector=null, officeDirector=null, officeDirectorPhone=null, officeStaffNum=null, officeEmpNum=null, coverPicUrl=k2l8zgqwstuxxevFX2qxVA==, journalPrice=null, startedYear=null, abbrevIsoEn=Journal of Computer Research and Development, journalRemark=null, publicationField=null, createdTime=1793776903141, updatedTime=1793850698612, createdBy=18614031015, updatedBy=13701087609, firstLetterCn=J, firstLetterEn=J, subjectCode=Electronic Information, subjectName=null, subjectCodeEn=Electronic Information, subjectNameEn=null, picCn=k2l8zgqwstuxxevFX2qxVA==, picEn=r6k0Ry+RD+c/VXj5QarmDw==, jcr=null, cjcr=null, exts=[JournalExt(id=1325069127710286688, language=CN, name=计算机研究与发展, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=, createdTime=1793850698640, updatedTime=1793850698640, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=https://crad.ict.ac.cn/journalx/authorLogOn.action, submissionEditorUrl=https://crad.ict.ac.cn/journalx/editorLogOn.action, submissionReviewUrl=https://crad.ict.ac.cn/journalx/expertLogOn.action, submissionCeEditorUrl=https://crad.ict.ac.cn/journalx/editorInChiefLogOn.action, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1325069127777395553, language=EN, name=Journal of Computer Research and Development, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=, createdTime=1793850698656, updatedTime=1793850698656, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=https://crad.ict.ac.cn/journalx/authorLogOn.action, submissionEditorUrl=https://crad.ict.ac.cn/journalx/editorLogOn.action, submissionReviewUrl=https://crad.ict.ac.cn/journalx/expertLogOn.action, submissionCeEditorUrl=https://crad.ict.ac.cn/journalx/editorInChiefLogOn.action, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1324759914146529478, websiteList=[Website(id=1325070300139892771, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1324759914146529478, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/jsjyjyfz/CN, language=CN, createTime=1793850978169, createBy=18614031015, updateTime=1793851040259, updateBy=18614031015, name=计算机研究与发展-中文, tplId=1146099689490845704, title=计算机研究与发展, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1325070893751349360, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=articleTextType, value=kx, createTime=1793851119697, updateTime=1793851119697, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893730377837, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=banner, value=null, createTime=1793851119692, updateTime=1793851119692, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893772320883, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=grayFlag, value=0, createTime=1793851119702, updateTime=1793851119702, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893721989228, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=logo, value=https://castjournals.cast.org.cn/joweb/jsjyjyfz/CN/file/pic?fileId=U27tDsy717YF7XSPA+Vwdw==, createTime=1793851119690, updateTime=1793851119690, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893784903797, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=minRunFlag, value=0, createTime=1793851119705, updateTime=1793851119705, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893742960751, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/jsjyjyfz/CN/file/pic, createTime=1793851119695, updateTime=1793851119695, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893780709492, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=silenceFlag, value=0, createTime=1793851119704, updateTime=1793851119704, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893738766446, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1793851119694, updateTime=1793851119694, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893755543665, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=themeColor, value=null, createTime=1793851119698, updateTime=1793851119698, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893763932274, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=themeStyle, value=null, createTime=1793851119700, updateTime=1793851119700, creator=18614031015, updator=18614031015)]), Website(id=1325070300580294698, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1324759914146529478, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN, language=EN, createTime=1793850978274, createBy=18614031015, updateTime=1793851036638, updateBy=18614031015, name=计算机研究与发展-英文, tplId=1146101810881728533, title=Journal of Computer Research and Development, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1325070925288321148, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=articleTextType, value=kx, createTime=1793851127216, updateTime=1793851127216, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925263155321, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=banner, value=null, createTime=1793851127210, updateTime=1793851127210, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925309292671, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=grayFlag, value=0, createTime=1793851127221, updateTime=1793851127221, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925254766712, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=logo, value=https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN/file/pic?fileId=U27tDsy717YF7XSPA+Vwdw==, createTime=1793851127208, updateTime=1793851127208, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925326069889, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=minRunFlag, value=0, createTime=1793851127225, updateTime=1793851127225, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925279932539, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN/file/pic, createTime=1793851127214, updateTime=1793851127214, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925317681280, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=silenceFlag, value=0, createTime=1793851127223, updateTime=1793851127223, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925271543930, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_en_623/, createTime=1793851127212, updateTime=1793851127212, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925292515453, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=themeColor, value=null, createTime=1793851127217, updateTime=1793851127217, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925300904062, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=themeStyle, value=null, createTime=1793851127219, updateTime=1793851127219, creator=18614031015, updator=18614031015)])], journalTitle=计算机研究与发展, weixinUrl=null, journalUrl=https://crad.ict.ac.cn/, iacademicId=null, status=1, seqNo=null, journalTitleEn=Journal of Computer Research and Development, journalPhotoCn=k2l8zgqwstuxxevFX2qxVA==, journalPhotoEn=r6k0Ry+RD+c/VXj5QarmDw==, journalFirstLetter=J, journalRecommend=null, journalNew=null, journalCollection=null, jcrJf=null, cjcrJf=null, jcrJfStr=null, cjcrJfStr=null, submissionFirstDecision=null, sciSubjectClassification=null, casSubjectClassification=null, citeScore=null, totalCitationFrequency=null, icpCode=null, psCode=null, advertisingLicenseCode=null, copyrightInformation=null, country=null, option=, provinceCode=null, provinceName=null, collectFlag=false, interPubPlatform=, interPubPlatformUrl=null), detailUrlCn=https://castjournals.cast.org.cn/joweb/jsjyjyfz/CN/10.7544/issn1000-1239.202550069, detailUrlEn=https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN/10.7544/issn1000-1239.202550069, pdfUrlCn=https://castjournals.cast.org.cn/joweb/jsjyjyfz/CN/PDF/10.7544/issn1000-1239.202550069, pdfUrlEn=https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN/PDF/10.7544/issn1000-1239.202550069, aliStartDate=0, aliEndDate=0, collectionFlag=false, citedCount=null, citedUrl=null, previewStatus=0, delFlag=0, hasFullText=1, orderTime=1767196800000, fullTextJson=null, articleText=null, reference=null)