Article(id=1329460998458684067, tenantId=1146029695717560320, journalId=1324759914146529478, issueId=1329460877864055544, articleNumber=null, orderNo=null, doi=10.7544/issn1000-1239.202330965, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1701360000000, receivedDateStr=2023-12-01, revisedDate=1708531200000, revisedDateStr=2024-02-22, acceptedDate=null, acceptedDateStr=null, onlineDate=1794897802223, onlineDateStr=2026-11-17, pubDate=1714492800000, pubDateStr=2024-05-01, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1794897802223, onlineIssueDateStr=2026-11-17, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1794897802223, creator=13701087609, updateTime=1794897802223, updator=13701087609, issue=Issue{id=1329460877864055544, tenantId=1146029695717560320, journalId=1324759914146529478, year='2024', volume='61', issue='5', pageStart='1085', pageEnd='1347', issueExtLink='null', onlineDate='null', pubDate='1714492800000', pubDateStr='2024-05-01', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1794897773471, creator='13701087609', updateTime=1794897773471, updator='13701087609', preIssue=null, nextIssue=null, articleTotal=null, ext=null, issueFiles=null, downloadFileDto=null}, startPage=1143, endPage=1155, ext={EN=ArticleExt(id=1329460998735508132, articleId=1329460998458684067, tenantId=1146029695717560320, journalId=1324759914146529478, language=EN, title=Safety Analysis of Large Model Content Generation Based on Knowledge Editing, columnId=1329460878547727097, journalTitle=Journal of Computer Research and Development, columnName=Special Issue on Large Models and Safety, runingTitle=null, highlight=null, articleAbstract=
Although large language models (LLMs) have achieved remarkable success, they still face security problems in practical applications, and it is easy to generate toxic and harmful content under malicious induction. Existing methods to mitigate the unsafe behavior of LLMs often demand significant computational resources and incur high costs associated with secure data collection. Knowledge editing offers a novel approach to constrain the model’s behavior precisely for specific inputs without the need for retraining, thus saving substantial resources. This approach provides a new feasible avenue for optimizing large models to generate secure content. Nevertheless, existing datasets for mitigating the unsafe behavior of LLMs do not encompass all unsafe scenarios. Moreover, the toxicity issues in these datasets are nearly insurmountable for post-alignment LLMs’ security defenses, hindering the optimization of safety concerns in post-alignment LLMs. In light of these challenges, we introduce a new dataset called SafeGen and propose a novel evaluation framework to analyze the potential of knowledge editing in optimizing the generation of secure content by LLMs. Extensive experiments reveal that knowledge editing demonstrates broad applications in rectifying unsafe behaviors exhibited by LLMs, and editing parameters can enhance the internal safety beliefs of LLMs. However, the fluency of text generated by knowledge editing falls short of expectations, indicating the inherent difficulty of this task. We hope that our work provides insights for the large model security community.
, authors=Mengru Wang
1, Yunzhi Yao
2, Zekun Xi
1, Jintian Zhang
1, Peng Wang
1, Ziwen Xu
1, Ningyu Zhang
1, 2, *, authorsList=Mengru Wang, Yunzhi Yao, Zekun Xi, Jintian Zhang, Peng Wang, Ziwen Xu, Ningyu Zhang, authorCompany=null, correspAuthors=Ningyu Zhang, authorNote=
born in 1996. PhD candidate. Member of CCF. Her main research interests include natural language processing, knowledge graph, and the safety of large language models
born in 2000. PhD candidate. Member of CCF. His main research interests include natural language processing, knowledge graph, and machine learning
born in 2001. Master. His main research interests include natural language processing and model editing
born in 2001. Master candidate. His main research interest includes natural language processing
born in 2001. Master. His main research interests include natural language processing, enhancement of large language models, and knowledge editing
born in 2002. Undergraduate. His main research interest includes natural language processing
born in 1989. PhD, associate professor. Senior member of CCF. His main research interests include knowledge graph and natural language processing
, correspAuthorsNote=null, copyrightStatement=Copyright © 2024 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=1329461002510381757, articleId=1329460998458684067, tenantId=1146029695717560320, journalId=1324759914146529478, language=CN, title=基于知识编辑的大模型内容生成安全分析, columnId=1329460878694527739, journalTitle=计算机研究与发展, columnName=大模型与安全专题, runingTitle=null, highlight=null, articleAbstract=
大语言模型(large language models,LLMs)虽然取得了显著的成功,但在实际应用中依然面临着安全问题,容易在恶意诱导下生成有毒、有害内容. 目前缓解LLMs不安全行为的方法通常需要高昂的数据收集成本以及大量的计算资源. 大模型知识编辑可以在不重新训练模型的基础上,根据特定的输入精确地改变模型对应的输出,在节约大量资源的条件下约束模型的行为;为优化大模型生成安全内容提供了一个新的可行思路. 然而,目前学术界缺乏较为系统和全面的基于知识编辑的大模型内容安全生成分析数据集. 具体地说,当前缓解LLMs不安全行为的数据集并未包括所有的不安全场景,且其有毒问题几乎无法绕过对齐后的LLMs安全防线,因此无法缓解对齐后LLMs存在的不安全问题. 针对上述问题,设计了新的数据集SafeGen,并提出新的评价体系分析知识编辑在优化LLMs生成安全内容的潜力. 大量的实验发现知识编辑可以提高LLMs内部的安全信念,在校正LLMs不安全行为领域展现了广阔的应用前景. 但经过知识编辑的LLMs生成文本的流畅性却差强人意,这也表明了这项任务的潜在难度. 该工作可以为大模型安全社区提供一些见解.
, authors=王梦如
1, 姚云志
2, 习泽坤
1, 张锦添
1, 王鹏
1, 徐子文
1, 张宁豫
1, 2, *, authorsList=王梦如, 姚云志, 习泽坤, 张锦添, 王鹏, 徐子文, 张宁豫, authorCompany=null, correspAuthors=张宁豫, authorNote=
 |
1996年生. 博士研究生. CCF 会员. 主要研究方向为自然语言处理、知识图谱、大语言模型安全 |
 |
2000 年生. 博士研究生. CCF 会员. 主要研究方向为自然语言处理、知识图谱、机器学习 |
 |
2001年生. 硕士. 主要研究方向为自然语言处理、模型编辑 |
 |
2001年生. 硕士研究生. 主要研究方向为自然语言处理 |
 |
2001年生. 硕士. 主要研究方向为自然语言处理、大型语言模型增强、知识编辑 |
 |
2002年生. 本科生. 主要研究方向为自然语言处理 |
 |
1989年生. 博士,副教授. CCF高级会员. 主要研究方向为知识图谱、自然语言处理 |
, correspAuthorsNote=
, copyrightStatement=版权所有 © 2024 计算机研究与发展编辑部, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=n08JBqgxGMxERiXpWwN/2Q==, magXml=IpxIvDqtza2kZqnLSlnMXg==, pdfUrl=null, pdf=KjM21wZPEQYGfx3afFE4ew==, pdfFileSize=1724915, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=pHmjBYxgZaA+CUjrs+kqQA==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=WTU/LLL8Flg7tKbII/6I2g==, mapNumber=null, fund=null)}, authors=[Author(id=1329461073587057048, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=mengruwg@zju.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1329461073654165914, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, authorId=1329461073587057048, language=EN, stringName=Mengru Wang, firstName=Mengru, middleName=null, lastName=Wang, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, address=
1School of Software Technology, Zhejiang University, Hangzhou 315048, bio={"content":"
born in 1996. PhD candidate. Member of CCF. Her main research interests include natural language processing, knowledge graph, and the safety of large language models
"}, bioImg=null, bioContent=
born in 1996. PhD candidate. Member of CCF. Her main research interests include natural language processing, knowledge graph, and the safety of large language models
, aboutCorrespAuthor=null), CN=AuthorExt(id=1329461073717080475, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, authorId=1329461073587057048, language=CN, stringName=王梦如, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, address=
1浙江大学软件学院 杭州 315048, bio={"img":"Pfx0uvCC0wyFwLlk1bu+3Q==","content":"
1996年生. 博士研究生. CCF 会员. 主要研究方向为自然语言处理、知识图谱、大语言模型安全
"}, bioImg=Pfx0uvCC0wyFwLlk1bu+3Q==, bioContent=
1996年生. 博士研究生. CCF 会员. 主要研究方向为自然语言处理、知识图谱、大语言模型安全
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1329461073448645009, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, xref=1, ext=[AuthorCompanyExt(id=1329461073457033618, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, companyId=1329461073448645009, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1School of Software Technology, Zhejiang University, Hangzhou 315048), AuthorCompanyExt(id=1329461073465422227, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, companyId=1329461073448645009, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1浙江大学软件学院 杭州 315048)])]), Author(id=1329461073792577949, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1329461073876464031, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, authorId=1329461073792577949, language=EN, stringName=Yunzhi Yao, firstName=Yunzhi, middleName=null, lastName=Yao, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
2, address=
2College of Computer Science and Technology, Zhejiang University, Hangzhou 310027, bio={"content":"
born in 2000. PhD candidate. Member of CCF. His main research interests include natural language processing, knowledge graph, and machine learning
"}, bioImg=null, bioContent=
born in 2000. PhD candidate. Member of CCF. His main research interests include natural language processing, knowledge graph, and machine learning
, aboutCorrespAuthor=null), CN=AuthorExt(id=1329461073956155808, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, authorId=1329461073792577949, language=CN, stringName=姚云志, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
2, address=
2浙江大学计算机科学与技术学院 杭州 310027, bio={"img":"5DPuiNX/kJCG+acQxaVYNg==","content":"
2000 年生. 博士研究生. CCF 会员. 主要研究方向为自然语言处理、知识图谱、机器学习
"}, bioImg=5DPuiNX/kJCG+acQxaVYNg==, bioContent=
2000 年生. 博士研究生. CCF 会员. 主要研究方向为自然语言处理、知识图谱、机器学习
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1329461073524142484, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, xref=2, ext=[AuthorCompanyExt(id=1329461073532531093, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, companyId=1329461073524142484, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
2College of Computer Science and Technology, Zhejiang University, Hangzhou 310027), AuthorCompanyExt(id=1329461073536725398, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, companyId=1329461073524142484, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
2浙江大学计算机科学与技术学院 杭州 310027)])]), Author(id=1329461074027458978, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, orderNo=2, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1329461074098762148, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, authorId=1329461074027458978, language=EN, stringName=Zekun Xi, firstName=Zekun, middleName=null, lastName=Xi, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, address=
1School of Software Technology, Zhejiang University, Hangzhou 315048, bio={"content":"
born in 2001. Master. His main research interests include natural language processing and model editing
"}, bioImg=null, bioContent=
born in 2001. Master. His main research interests include natural language processing and model editing
, aboutCorrespAuthor=null), CN=AuthorExt(id=1329461074157482405, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, authorId=1329461074027458978, language=CN, stringName=习泽坤, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, address=
1浙江大学软件学院 杭州 315048, bio={"img":"IhsGrAlMz9fDO9oKGZWR8A==","content":"
2001年生. 硕士. 主要研究方向为自然语言处理、模型编辑
"}, bioImg=IhsGrAlMz9fDO9oKGZWR8A==, bioContent=
2001年生. 硕士. 主要研究方向为自然语言处理、模型编辑
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1329461073448645009, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, xref=1, ext=[AuthorCompanyExt(id=1329461073457033618, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, companyId=1329461073448645009, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1School of Software Technology, Zhejiang University, Hangzhou 315048), AuthorCompanyExt(id=1329461073465422227, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, companyId=1329461073448645009, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1浙江大学软件学院 杭州 315048)])]), Author(id=1329461074224591271, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, orderNo=3, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1329461074300088745, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, authorId=1329461074224591271, language=EN, stringName=Jintian Zhang, firstName=Jintian, middleName=null, lastName=Zhang, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, address=
1School of Software Technology, Zhejiang University, Hangzhou 315048, bio={"content":"
born in 2001. Master candidate. His main research interest includes natural language processing
"}, bioImg=null, bioContent=
born in 2001. Master candidate. His main research interest includes natural language processing
, aboutCorrespAuthor=null), CN=AuthorExt(id=1329461074363003306, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, authorId=1329461074224591271, language=CN, stringName=张锦添, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, address=
1浙江大学软件学院 杭州 315048, bio={"img":"LxLXZ7RFxJyrNF6Hlw4KMw==","content":"
2001年生. 硕士研究生. 主要研究方向为自然语言处理
"}, bioImg=LxLXZ7RFxJyrNF6Hlw4KMw==, bioContent=
2001年生. 硕士研究生. 主要研究方向为自然语言处理
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1329461073448645009, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, xref=1, ext=[AuthorCompanyExt(id=1329461073457033618, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, companyId=1329461073448645009, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1School of Software Technology, Zhejiang University, Hangzhou 315048), AuthorCompanyExt(id=1329461073465422227, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, companyId=1329461073448645009, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1浙江大学软件学院 杭州 315048)])]), Author(id=1329461074442695084, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, orderNo=4, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1329461074513998254, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, authorId=1329461074442695084, language=EN, stringName=Peng Wang, firstName=Peng, middleName=null, lastName=Wang, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, address=
1School of Software Technology, Zhejiang University, Hangzhou 315048, bio={"content":"
born in 2001. Master. His main research interests include natural language processing, enhancement of large language models, and knowledge editing
"}, bioImg=null, bioContent=
born in 2001. Master. His main research interests include natural language processing, enhancement of large language models, and knowledge editing
, aboutCorrespAuthor=null), CN=AuthorExt(id=1329461074589495727, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, authorId=1329461074442695084, language=CN, stringName=王鹏, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, address=
1浙江大学软件学院 杭州 315048, bio={"img":"7DImsqV8L0YezrV8OwmNcg==","content":"
2001年生. 硕士. 主要研究方向为自然语言处理、大型语言模型增强、知识编辑
"}, bioImg=7DImsqV8L0YezrV8OwmNcg==, bioContent=
2001年生. 硕士. 主要研究方向为自然语言处理、大型语言模型增强、知识编辑
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1329461073448645009, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, xref=1, ext=[AuthorCompanyExt(id=1329461073457033618, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, companyId=1329461073448645009, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1School of Software Technology, Zhejiang University, Hangzhou 315048), AuthorCompanyExt(id=1329461073465422227, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, companyId=1329461073448645009, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1浙江大学软件学院 杭州 315048)])]), Author(id=1329461074652410289, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, orderNo=5, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1329461074736296371, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, authorId=1329461074652410289, language=EN, stringName=Ziwen Xu, firstName=Ziwen, middleName=null, lastName=Xu, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, address=
1School of Software Technology, Zhejiang University, Hangzhou 315048, bio={"content":"
born in 2002. Undergraduate. His main research interest includes natural language processing
"}, bioImg=null, bioContent=
born in 2002. Undergraduate. His main research interest includes natural language processing
, aboutCorrespAuthor=null), CN=AuthorExt(id=1329461074815988148, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, authorId=1329461074652410289, language=CN, stringName=徐子文, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, address=
1浙江大学软件学院 杭州 315048, bio={"img":"36x6sDLzN3cEbiyiDzncXQ==","content":"
2002年生. 本科生. 主要研究方向为自然语言处理
"}, bioImg=36x6sDLzN3cEbiyiDzncXQ==, bioContent=
2002年生. 本科生. 主要研究方向为自然语言处理
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1329461073448645009, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, xref=1, ext=[AuthorCompanyExt(id=1329461073457033618, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, companyId=1329461073448645009, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1School of Software Technology, Zhejiang University, Hangzhou 315048), AuthorCompanyExt(id=1329461073465422227, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, companyId=1329461073448645009, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1浙江大学软件学院 杭州 315048)])]), Author(id=1329461074887291318, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, orderNo=6, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=zhangningyug@zju.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1329461074971177401, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, authorId=1329461074887291318, language=EN, stringName=Ningyu Zhang, firstName=Ningyu, middleName=null, lastName=Zhang, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, 2, *, address=
1School of Software Technology, Zhejiang University, Hangzhou 315048
2College of Computer Science and Technology, Zhejiang University, Hangzhou 310027, bio={"content":"
born in 1989. PhD, associate professor. Senior member of CCF. His main research interests include knowledge graph and natural language processing
"}, bioImg=null, bioContent=
born in 1989. PhD, associate professor. Senior member of CCF. His main research interests include knowledge graph and natural language processing
, aboutCorrespAuthor=null), CN=AuthorExt(id=1329461075034091962, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, authorId=1329461074887291318, language=CN, stringName=张宁豫, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, 2, *, address=
1浙江大学软件学院 杭州 315048
2浙江大学计算机科学与技术学院 杭州 310027, bio={"img":"oSHBPl5BsC4UgTf+FH2FrA==","content":"
1989年生. 博士,副教授. CCF高级会员. 主要研究方向为知识图谱、自然语言处理
"}, bioImg=oSHBPl5BsC4UgTf+FH2FrA==, bioContent=
1989年生. 博士,副教授. CCF高级会员. 主要研究方向为知识图谱、自然语言处理
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1329461073448645009, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, xref=1, ext=[AuthorCompanyExt(id=1329461073457033618, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, companyId=1329461073448645009, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1School of Software Technology, Zhejiang University, Hangzhou 315048), AuthorCompanyExt(id=1329461073465422227, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, companyId=1329461073448645009, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1浙江大学软件学院 杭州 315048)]), AuthorCompany(id=1329461073524142484, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, xref=2, ext=[AuthorCompanyExt(id=1329461073532531093, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, companyId=1329461073524142484, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
2College of Computer Science and Technology, Zhejiang University, Hangzhou 310027), AuthorCompanyExt(id=1329461073536725398, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, companyId=1329461073524142484, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
2浙江大学计算机科学与技术学院 杭州 310027)])])], keywords=[Keyword(id=1329461075168309691, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, language=EN, orderNo=1, keyword=large language model), Keyword(id=1329461076774728125, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, language=EN, orderNo=2, keyword=safety), Keyword(id=1329461076837642686, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, language=EN, orderNo=3, keyword=knowledge editing), Keyword(id=1329461076908945855, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, language=EN, orderNo=4, keyword=content generation), Keyword(id=1329461076984443328, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, language=EN, orderNo=5, keyword=jailbreak prompt), Keyword(id=1329461077047357889, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, language=EN, orderNo=6, keyword=defense), Keyword(id=1329461077118661058, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, language=EN, orderNo=7, keyword=dataset), Keyword(id=1329461077185769923, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, language=CN, orderNo=1, keyword=大语言模型), Keyword(id=1329461077269656004, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, language=CN, orderNo=2, keyword=安全), Keyword(id=1329461077332570565, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, language=CN, orderNo=3, keyword=知识编辑), Keyword(id=1329461077387096518, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, language=CN, orderNo=4, keyword=内容生成), Keyword(id=1329461077454205383, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, language=CN, orderNo=5, keyword=越狱提示), Keyword(id=1329461077512925640, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, language=CN, orderNo=6, keyword=防御), Keyword(id=1329461077575840201, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, language=CN, orderNo=7, keyword=数据集)], refs=[Reference(id=1329461079354225114, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, 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=Huang Jie, Chang Kevin Chen-Chuan. Towards reasoning in large language models: A survey [C]// Proc of Findings of the Association for Computational Linguistics. Stroudsburg, PA: ACL, 2023: 1049−1065, articleTitle=null, refAbstract=null), Reference(id=1329461079421333979, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, 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=Mori M, MacDorman K, Kageki N. The uncanny valley from the field[J]. IEEE Robotics & Automation Magazine, 2012, 19(2): 98−100, articleTitle=null, refAbstract=null), Reference(id=1329461079488442844, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, 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=Zhang Zhexin, Lei Leqi, Wu Lindong, et al. Safetybench: Evaluating the safety of large language models with multiple choice questions[J]. arXiv preprint, arXiv: 2309.07045, 2023, articleTitle=null, refAbstract=null), Reference(id=1329461079551357405, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, 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=Sun Hao, Zhang Zhexin, Deng Jiawen, et al. Safety assessment of Chinese large language models[J]. arXiv preprint, arXiv: 2304.10436, 2023, articleTitle=null, refAbstract=null), Reference(id=1329461079614271966, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, 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=Deshpande A, Murahari V, Rajpurohit T, et al. Toxicity in ChatGPT: Analyzing persona-assigned language models [J]. arXiv preprint, arXiv: 2304.05335, 2023, articleTitle=null, refAbstract=null), Reference(id=1329461081245856224, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=6, rfOrder=5, authorNames=null, journalName=null, refType=null, unstructuredReference=矣晓沅,谢幸. 大模型道德价值观对齐问题剖析[J]. 计算机研究与发展,2023,60(9):1926−1945, articleTitle=null, refAbstract=null), Reference(id=1329461081371685345, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, 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=Yi Xiaoyuan, Xie Xing. Unpacking the ethical value alignment in big models[J]. Journal of Computer Research and Development, 2023, 60(9): 1926−1945 (in Chinese), articleTitle=null, refAbstract=null), Reference(id=1329461081434599906, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=7, rfOrder=7, authorNames=null, journalName=null, refType=null, unstructuredReference=Xi Zhihen, Chen Wenxiang, Guo Xin, et al. The rise and potential of large language model based agents: A survey[J]. arXiv preprint, arXiv: 2309.07864, 2023, articleTitle=null, refAbstract=null), Reference(id=1329461081501708771, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=8, rfOrder=8, authorNames=null, journalName=null, refType=null, unstructuredReference=Xu Guohai, Liu Jiay, Yan Ming, et al. Cvalues: Measuring the values of Chinese large language models from safety to responsibility[J]. arXiv preprint, arXiv: 2307.09705, 2023, articleTitle=null, refAbstract=null), Reference(id=1329461081568817636, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=9, rfOrder=9, authorNames=null, journalName=null, refType=null, unstructuredReference=Khalatbari L, Bang Yejin, Su Dan, et al. Learn What NOT to learn: Towards generative safety in Chatbots[J]. arXiv preprint, arXiv: 2304.11220, 2023, articleTitle=null, refAbstract=null), Reference(id=1329461081661092325, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=10, rfOrder=10, authorNames=null, journalName=null, refType=null, unstructuredReference=Balestriero R, Cosentino R, Shekkizhar S. Characterizing large language model geometry solves toxicity detection and generation[J]. arXiv preprint, arXiv: 2312.01648, 2023, articleTitle=null, refAbstract=null), Reference(id=1329461081719812582, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=11, rfOrder=11, authorNames=null, journalName=null, refType=null, unstructuredReference=Li Xingxuan, Li Yutong, Shafiq J, et al. Does GPT-3 demonstrate psychopathy? Evaluating large language models from a psychological perspective[J]. arXiv preprint, arXiv: 2212.10529, 2023, articleTitle=null, refAbstract=null), Reference(id=1329461081782727143, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=12, rfOrder=12, authorNames=null, journalName=null, refType=null, unstructuredReference=Lu Ximing, Sean W, Jack H, et al. Quark: Controllable text generation with reinforced unlearning[J]. Advances in Neural Information Processing Systems, 2022, 35: 27591−27609, articleTitle=null, refAbstract=null), Reference(id=1329461081845641704, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=13, rfOrder=13, authorNames=null, journalName=null, refType=null, unstructuredReference=Unanue I J, Parnell J, Piccardi M. BERTTune: Fine-tuning neural machine translation with BERTScore[J]. arXiv preprint, arXiv: 2106.02208, 2021, articleTitle=null, refAbstract=null), Reference(id=1329461081904361961, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=14, rfOrder=14, authorNames=null, journalName=null, refType=null, unstructuredReference=Scheurer J, Campos J A, Korbak T, et al. Training language models with language feedback at scale[J]. arXiv preprint, arXiv: 2303.16755, 2023, articleTitle=null, refAbstract=null), Reference(id=1329461081967276522, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=15, rfOrder=15, authorNames=null, journalName=null, refType=null, unstructuredReference=Wu Zeqiu, Hu Yushi, Shi Weijia, et al. Fine-grained human feedback gives better rewards for language model training[J]. arXiv preprint, arXiv: 2306.01693, 2023, articleTitle=null, refAbstract=null), Reference(id=1329461082025996779, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=16, rfOrder=16, authorNames=null, journalName=null, refType=null, unstructuredReference=Ouyang Long, Jeff W, Jiang Xu, et al. Training language models to follow instructions with human feedback[J]. Advances in Neural Information Processing Systems, 2022, 35: 27730−27744, articleTitle=null, refAbstract=null), Reference(id=1329461082097299948, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=17, rfOrder=17, authorNames=null, journalName=null, refType=null, unstructuredReference=Shen Wei, Zheng Rui, Zhan Wenyu, et al. Loose lips sink ships: Mitigating length bias in reinforcement earning from human feedback[J]. arXiv preprint, arXiv: 2310.05199, 2023, articleTitle=null, refAbstract=null), Reference(id=1329461082181186029, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=18, rfOrder=18, authorNames=null, journalName=null, refType=null, unstructuredReference=Yu Jiahao, Lin Xingwei, Yu Zheng, et al. Gptfuzzer: Red teaming large language models with auto-generated jailbreak prompts[J]. arXiv preprint, arXiv: 2309.10253, 2023, articleTitle=null, refAbstract=null), Reference(id=1329461082256683502, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=19, rfOrder=19, authorNames=null, journalName=null, refType=null, unstructuredReference=Liu Yi, Deng Gelei, Xu Zhengzi, et al. Jailbreaking chatgpt via prompt engineering: An empirical study[J]. arXiv preprint, arXiv: 2305.13860, 2023, articleTitle=null, refAbstract=null), Reference(id=1329461082315403759, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=20, rfOrder=20, authorNames=null, journalName=null, refType=null, unstructuredReference=Akyurek A, Akyurek E, Kalyan A, et al. RL4F: Generating natural language feedback with reinforcement learning for repairing model outputs[J]. arXiv preprint, arXiv: 2305.08844, 2023, articleTitle=null, refAbstract=null), Reference(id=1329461082378318320, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=21, rfOrder=21, authorNames=null, journalName=null, refType=null, unstructuredReference=Huang Yangsibo, Gupta S, Xia Mengzhou, et al. Catastrophic jailbreak of open-source LLMs via exploiting generation[J]. arXiv preprint, arXiv: 2310.06987, 2023, articleTitle=null, refAbstract=null), Reference(id=1329461082449621489, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=22, rfOrder=22, authorNames=null, journalName=null, refType=null, unstructuredReference=Wen Jiaxin, Ke Pei, Sun Hao, et al. Unveiling the implicit toxicity in large language models[J]. arXiv preprint, arXiv: 2311.17391, 2023, articleTitle=null, refAbstract=null), Reference(id=1329461082512536050, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=23, rfOrder=23, authorNames=null, journalName=null, refType=null, unstructuredReference=Madaan A, Tandon N, Gupta P, et al. Self-refine: Iterative refinement with self-feedback[J]. arXiv preprint, arXiv: 2303.17651, 2023, articleTitle=null, refAbstract=null), Reference(id=1329461082575450611, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=24, rfOrder=24, authorNames=null, journalName=null, refType=null, unstructuredReference=Welleck S, Lu Ximing, West P, et al. Generating sequences by learning to self-correct[J]. arXiv preprint, arXiv: 2211.00053, 2022, articleTitle=null, refAbstract=null), Reference(id=1329461082646753780, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=25, rfOrder=25, authorNames=null, journalName=null, refType=null, unstructuredReference=Gandikota R, Materzynska J, Fiotto-Kaufman J, et al. Erasing concepts from diffusion models[C]// Proc of Int Conf on Computer Vision. Piscataway, NJ: IEEE, 2023: 2426−2436, articleTitle=null, refAbstract=null), Reference(id=1329461082722251253, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=26, rfOrder=26, authorNames=null, journalName=null, refType=null, unstructuredReference=Yao Yunzhi, Wang Peng, Tian Bozhong, et al. Editing large language models: Problems, methods, and opportunities[C] // Empirical Methods in Natural Language Processing. Stroudsburg, PA: EMNLP, 2023: 10222−10240, articleTitle=null, refAbstract=null), Reference(id=1329461082785165814, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=27, rfOrder=27, authorNames=null, journalName=null, refType=null, unstructuredReference=Geva M, Caciularu A, Wang K R, et al. Transformer feed-forward layers build predictions by promoting concepts in the vocabulary space[C]// Empirical Methods in Natural Language Processing. Stroudsburg, PA: EMNLP, 2022: 30−45, articleTitle=null, refAbstract=null), Reference(id=1329461082852274679, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=28, rfOrder=28, authorNames=null, journalName=null, refType=null, unstructuredReference=Hu Xinshuo, Li Dongfang, Hu Baotian, et al. Separate the wheat from the chaff: Model deficiency unlearning via parameter-efficient module operation[J]. arXiv preprint, arXiv: 2308.08090, 2023, articleTitle=null, refAbstract=null), Reference(id=1329461082931966456, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=29, rfOrder=29, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhang Yizhe, Galley M, Gao Jianfeng, et al. Generating informative and diverse conversational responses via adversarial information maximization[C]// Advances in Neural Information Processing Systems. La Jolla, CA: NEURAL INFORMATION PROCESSING SYSTEMS , 2018: 31−56, articleTitle=null, refAbstract=null), Reference(id=1329461083011658233, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=30, rfOrder=30, authorNames=null, journalName=null, refType=null, unstructuredReference=Heryanto Y, Triayudi A. Evaluating text quality of GPT engine davinci-003 and GPT engine davinci generation using BLEU score[J]. SAGA: Journal of Technology and Information System, 2023, 1(4): 121−129, articleTitle=null, refAbstract=null), Reference(id=1329461083082961402, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=31, rfOrder=31, authorNames=null, journalName=null, refType=null, unstructuredReference=Tang Zecheng, Zhou Keyan, Wang Pinzheng, et al. Detoxify language model step-by-step[J]. arXiv preprint, arXiv: 2308.08295, 2023, articleTitle=null, refAbstract=null), Reference(id=1329461083137487355, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=32, rfOrder=32, authorNames=null, journalName=null, refType=null, unstructuredReference=Shu Manli, Wang Jiongxiao, Zhu Chen, et al. On the exploitability of instruction tuning[J]. arXiv preprint, arXiv: 2306.17194, 2023, articleTitle=null, refAbstract=null), Reference(id=1329461083200401916, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=33, rfOrder=33, authorNames=null, journalName=null, refType=null, unstructuredReference=Wu Xinwei, Li Junzhuo, Xu Minghui, et al. DEPN: Detecting and editing privacy neurons in pretrained language models[C]// Empirical Methods in Natural Language Processing. Stroudsburg, PA: EMNLP, 2023: 2875–2886, articleTitle=null, refAbstract=null), Reference(id=1329461083259122173, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=34, rfOrder=34, authorNames=null, journalName=null, refType=null, unstructuredReference=Ishibashi Y, Shimodaira H. Knowledge sanitization of large language models[J]. arXiv preprint, arXiv: 2309.11852, 2023, articleTitle=null, refAbstract=null), Reference(id=1329461083317842430, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=35, rfOrder=35, authorNames=null, journalName=null, refType=null, unstructuredReference=Meng K, Bau D, Andonian A, et al. Locating and editing factual associations in GPT[C]//Advances in Neural Information Processing Systems. New York: Curran Associates, 2022: 17359−17372, articleTitle=null, refAbstract=null), Reference(id=1329461083376562687, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=36, rfOrder=36, authorNames=null, journalName=null, refType=null, unstructuredReference=Mitchell E, Lin C, Bosselut A. Memory-based model editing at scale [C]//Proc of Int Conf on Machine Learning. New York: ACM, 2022: 15817−15831, articleTitle=null, refAbstract=null), Reference(id=1329461083443671552, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=37, rfOrder=37, authorNames=null, journalName=null, refType=null, unstructuredReference=Mitchell E, Lin C, Bosselut A, et al. Fast model editing at scale[J]. arXiv preprint, arXiv: 2110.11309, 2021, articleTitle=null, refAbstract=null), Reference(id=1329461083510780417, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=38, rfOrder=38, authorNames=null, journalName=null, refType=null, unstructuredReference=Zheng Ce, Li Lei, Dong Qingxiu, et al. Can we edit factual knowledge by in-context learning? [C]// Proc of Conf on Empirical Methods in Natural Language Processing. Stroudsburg, PA: EMNLP, 2023: 4862−4876, articleTitle=null, refAbstract=null), Reference(id=1329461083594666498, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=39, rfOrder=39, authorNames=null, journalName=null, refType=null, unstructuredReference=Mei A, Levy S, Wang W Y. ASSERT: Automated safety scenario red teaming for evaluating the robustness of large language models [J]. arXiv preprint, arXiv: 2310.09624, 2023, articleTitle=null, refAbstract=null), Reference(id=1329461083653386755, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=40, rfOrder=40, authorNames=null, journalName=null, refType=null, unstructuredReference=Glaese A, McAleese N, Trębacz M, et al. Improving alignment of dialogue agents via targeted human judgements [J]. arXiv preprint, arXiv: 2209.14375, 2022, articleTitle=null, refAbstract=null), Reference(id=1329461083724689924, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=41, rfOrder=41, authorNames=null, journalName=null, refType=null, unstructuredReference=Wan D, Bansal M. FactPEGASUS: Factuality-aware pre-training and fine-tuning for abstractive summarization[C]// Proc of Conf of the North American Chapter of the Association for Computational Linguisti. Stroudsburg, PA : ACL, 2022: 1010−1028, articleTitle=null, refAbstract=null), Reference(id=1329461083791798789, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=42, rfOrder=42, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhu Xinyu, Wang Junjie, Zhang Lin, et al. Solving math word problems via cooperative reasoning induced language models[C]//Proc of the 61st Annual Meeting of the Association for Computational Linguistics. Stroudsburg, PA : ACL, 2023: 4471−4485, articleTitle=null, refAbstract=null), Reference(id=1329461083858907654, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=43, rfOrder=43, authorNames=null, journalName=null, refType=null, unstructuredReference=Dathathri S, Madotto A, Lan J, et al. Plug and play language models: A simple approach to controlled text generation[J]. arXiv preprint, arXiv: 1912.02164, 2019, articleTitle=null, refAbstract=null), Reference(id=1329461083917627911, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=44, rfOrder=44, authorNames=null, journalName=null, refType=null, unstructuredReference=Huang Zeyu, Shen Yikang, Zhang Xiaofeng, et al. Transformer-patcher: One mistake worth one neuron[C]//Proc of the 11th Int Conf on Learning Representations. [2023-01-24]. https://arxiv.org/pdf/2301.09785.pdf, articleTitle=null, refAbstract=null), Reference(id=1329461083988931081, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=45, rfOrder=45, authorNames=null, journalName=null, refType=null, unstructuredReference=Meng K, Sharma A S, Andonian A, et al. Mass-editing memory in a transformer[C] //Proc of the 11th Int Conf on Learning Representations.[2023-08-01].https://arxiv.org/pdf/2210.07229.pdf., articleTitle=null, refAbstract=null)], funds=null, companyList=[AuthorCompany(id=1329461073448645009, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, xref=1, ext=[AuthorCompanyExt(id=1329461073457033618, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, companyId=1329461073448645009, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1School of Software Technology, Zhejiang University, Hangzhou 315048), AuthorCompanyExt(id=1329461073465422227, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, companyId=1329461073448645009, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1浙江大学软件学院 杭州 315048)]), AuthorCompany(id=1329461073524142484, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, xref=2, ext=[AuthorCompanyExt(id=1329461073532531093, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, companyId=1329461073524142484, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
2College of Computer Science and Technology, Zhejiang University, Hangzhou 310027), AuthorCompanyExt(id=1329461073536725398, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, companyId=1329461073524142484, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
2浙江大学计算机科学与技术学院 杭州 310027)])], figs=[ArticleFig(id=1329461077802332618, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, language=EN, label=Figure 1, caption=
The illustration of knowledge editing calibrating LLMs to generate safe context, figureFileSmall=vjfIC6Kksx3c+cy84i48Kg==, figureFileBig=pHmjBYxgZaA+CUjrs+kqQA==, tableContent=null), ArticleFig(id=1329461077949133259, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, language=CN, label=图1, caption=
知识编辑优化LLMs生成安全内容的示意图, figureFileSmall=vjfIC6Kksx3c+cy84i48Kg==, figureFileBig=pHmjBYxgZaA+CUjrs+kqQA==, tableContent=null), ArticleFig(id=1329461078058185164, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, language=EN, label=Figure 2, caption=
Flowchart of SafeGen dataset construction, figureFileSmall=kJEfngxbIuihJtitJQPYvg==, figureFileBig=5WWKOLl7HamTmbe6VEzMQA==, tableContent=null), ArticleFig(id=1329461078167237069, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, language=CN, label=图2, caption=
SafeGen数据集构建流程图, figureFileSmall=kJEfngxbIuihJtitJQPYvg==, figureFileBig=5WWKOLl7HamTmbe6VEzMQA==, tableContent=null), ArticleFig(id=1329461078238540238, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, language=EN, label=Figure 3, caption=
Case 954 in SafeGen, figureFileSmall=nKhREiwV4mEN1bzw79Yh5g==, figureFileBig=DB9d7rBkoZ7uPPMCZ9rxDw==, tableContent=null), ArticleFig(id=1329461078314037711, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, language=CN, label=图3, caption=
SafeGen中的第954个实例, figureFileSmall=nKhREiwV4mEN1bzw79Yh5g==, figureFileBig=DB9d7rBkoZ7uPPMCZ9rxDw==, tableContent=null), ArticleFig(id=1329461078431478224, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, language=EN, label=Figure 4, caption=
The performance of different jailbreak prompts, figureFileSmall=HnZbxBc/j6scp0j0hp5F8g==, figureFileBig=wS7CkmCQm4VKqduNPMoWPQ==, tableContent=null), ArticleFig(id=1329461078486004177, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, language=CN, label=图4, caption=
不同越狱提示的性能, figureFileSmall=HnZbxBc/j6scp0j0hp5F8g==, figureFileBig=wS7CkmCQm4VKqduNPMoWPQ==, tableContent=null), ArticleFig(id=1329461078578278866, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, language=EN, label=Figure 5, caption=
Case analysis of the editing SafeGen with MEND on LLaMA2-13B-Chat for illegal activity, figureFileSmall=wlQPYKL+nKqAXn9qRm2amg==, figureFileBig=lNhtB+yDKxH9CgiGW4CX6g==, tableContent=null), ArticleFig(id=1329461078657970643, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, language=CN, label=图5, caption=
MEND在LLaMA2-13B-Chat上编辑SafeGen中违法活动的案例分析, figureFileSmall=wlQPYKL+nKqAXn9qRm2amg==, figureFileBig=lNhtB+yDKxH9CgiGW4CX6g==, tableContent=null), ArticleFig(id=1329461078733468116, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, language=EN, label=Table 1, caption=
Statistics of SafeGen Dataset
, figureFileSmall=null, figureFileBig=null, tableContent=
| 类别(CATEGORY) | 描述(DESCRIPTION) | 数量 |
|---|
| 冒犯 | 威胁、侮辱、蔑视、亵渎、讽刺以及无礼的行为 | 594 |
| 偏见和不公平 | 种族、性别、宗教等各种话题的社会偏见 | 594 |
| 物理伤害 | 可能影响人体健康的行为 | 594 |
| 精神伤害 | 与心理、精神、情绪、心态等有关的健康问题 | 594 |
| 非法活动 | 违法行为,可能造成不良社会影响 | 594 |
| 伦理道德 | 不道德行为,但不违法的行为 | 594 |
| 隐私与财产 | 涉及隐私、财产、投资等问题 | 594 |
), ArticleFig(id=1329461078804771285, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, language=CN, label=表1, caption=
SafeGen数据集统计
, figureFileSmall=null, figureFileBig=null, tableContent=
| 类别(CATEGORY) | 描述(DESCRIPTION) | 数量 |
|---|
| 冒犯 | 威胁、侮辱、蔑视、亵渎、讽刺以及无礼的行为 | 594 |
| 偏见和不公平 | 种族、性别、宗教等各种话题的社会偏见 | 594 |
| 物理伤害 | 可能影响人体健康的行为 | 594 |
| 精神伤害 | 与心理、精神、情绪、心态等有关的健康问题 | 594 |
| 非法活动 | 违法行为,可能造成不良社会影响 | 594 |
| 伦理道德 | 不道德行为,但不违法的行为 | 594 |
| 隐私与财产 | 涉及隐私、财产、投资等问题 | 594 |
), ArticleFig(id=1329461078871880150, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, language=EN, label=Table 2, caption=
The Difference Between SafeGen and Existing Datasets
, figureFileSmall=null, figureFileBig=null, tableContent=
| 数据集 | 有害问题 | 越狱提示 | 有毒回复 | 安全回复 | 是非观 | 事实问答 | 不安全 类别 | 能否绕过Chat模型 |
|---|
| SafeGen | √ | √ | √ | √ | √ | √ | 7类 | 大概率可以 |
| 攻击数据集[3-4] | √ | √ | × | √ | × | × | 7类 | 大概率可以 |
| 防御数据集[31-32] | √ | 大部分有 | × | √ | × | × | 缺少部分 | 大概率可以 |
| 祛毒数据集[28,33-34] | √ | × | × | √ | × | × | 缺少部分 | 几乎不能 |
), ArticleFig(id=1329461078964154839, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, language=CN, label=表2, caption=
SafeGen与现存数据集之间的差异
, figureFileSmall=null, figureFileBig=null, tableContent=
| 数据集 | 有害问题 | 越狱提示 | 有毒回复 | 安全回复 | 是非观 | 事实问答 | 不安全 类别 | 能否绕过Chat模型 |
|---|
| SafeGen | √ | √ | √ | √ | √ | √ | 7类 | 大概率可以 |
| 攻击数据集[3-4] | √ | √ | × | √ | × | × | 7类 | 大概率可以 |
| 防御数据集[31-32] | √ | 大部分有 | × | √ | × | × | 缺少部分 | 大概率可以 |
| 祛毒数据集[28,33-34] | √ | × | × | √ | × | × | 缺少部分 | 几乎不能 |
), ArticleFig(id=1329461079035458008, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, language=EN, label=Table 3, caption=
The Results of Various Knowledge Editing Methods on SafeGen Dataset
, figureFileSmall=null, figureFileBig=null, tableContent=
| 基座模型 | 方法 | 成功率/%↑ | 泛化性/%↑ | 流畅性/%↑ | 是非观/%↑ | 局部性/%↑ |
|---|
| GPT-J-6B | None | 41.02 | 40.86 | 4.72 | 13.09 | 100.00 |
| FT | 36.71(−4.31) | 35.03(−5.83) | 4.34(−0.39) | 12.89(−0.20) | 99.55(−0.45) |
| SERAC | 91.91(50.89) | 80.61(39.75) | 6.55(1.83) | 48.81(35.72) | 100(0.00) |
| MEND | 95.93(54.91) | 74.24(33.38) | 2.56(−2.17) | 6.90(−6.19) | 96.08(−3.92) |
| Ext-Sub | 55.47(14.45) | 59.94(19.08) | 4.23(−0.50) | 15.56(2.47) | 97.71(−2.29) |
| IKE | 36.47(−4.55) | 25.78(−15.08) | 5.11(−0.39) | 12.33(−0.76) | 78.66(−21.34) |
| LLaMA2-7B | None | 33.68 | 34.16 | 7.44 | 40.42 | 100.00 |
| FT | 77.66(43.98) | 57.70(23.54) | 6.58(−0.86) | 39.78(−0.64) | 96.93(−3.07) |
| SERAC | 99.60(65.92) | 98.56(50.65) | 5.37(−2.08) | 31.05(−9.37) | 100(0.00) |
| MEND | 99.04(65.36) | 89.31(41.40) | 6.42(−1.02) | 21.71(−18.71) | 98.30(−1.70) |
| Ext-Sub | 67.92(34.24) | 68.56(20.65) | 7.95(−0.16) | 45.17(4.75) | 98.65(−1.35) |
| IKE | 38.31(4.63) | 33.84(−14.07) | 7.41(−0.03) | 41.90(1.48) | 84.77(−15.23) |
| LLaMA2-7B-Chat | None | 44.53 | 48.44 | 6.57 | 84.32 | 100 |
| FT | 79.89(35.36) | 58.70(10.26) | 7.18(0.61) | 85.24(0.92) | 96.00(−4.00) |
| SERAC | 99.60(55.07) | 98.56(50.65) | 5.37(−1.21) | 31.05(−53.27) | 100(0.00) |
| MEND | 94.41(49.88) | 75.42(27.51) | 6.94(0.37) | 76.94(−7.38) | 97.99(−2.01) |
| Ext-Sub | 61.29(16.76) | 62.17(14.26) | 7.53(0.96) | 84.78(0.46) | 97.92(−2.08) |
| IKE | 67.83(23.30) | 49.32(1.41) | 8.24(1.67) | 85.67(1.35) | 84.77(−15.23) |
| LLaMA2-13B-Chat | None | 47.91 | 50.43 | 7.39 | 81.79 | 100.00 |
| FT | 75.96(28.05) | 58.07(7.64) | 7.44(0.05) | 82.91(1.12) | 96.71(−3.29) |
| SERAC | 99.60(51.69) | 98.56(48.13) | 5.37(−2.02) | 31.05(−50.74) | 100.00(0.00) |
| MEND | 85.63(37.72) | 60.26(9.83) | 7.25(−0.14) | 81.17(−0.62) | 98.75(−1.25) |
| Ext-Sub | 73.18(25.27) | 73.02(22.59) | 7.52(0.14) | 81.92(0.13) | 99.08(−0.92) |
| IKE | 57.04(9.13) | 43.60(−6.83) | 8.75(1.37) | 51.84(−29.95) | 77.10(−22.90) |
), ArticleFig(id=1329461079119344089, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329460998458684067, language=CN, label=表3, caption=
不同知识编辑方法在SafeGen数据集的结果
, figureFileSmall=null, figureFileBig=null, tableContent=
| 基座模型 | 方法 | 成功率/%↑ | 泛化性/%↑ | 流畅性/%↑ | 是非观/%↑ | 局部性/%↑ |
|---|
| GPT-J-6B | None | 41.02 | 40.86 | 4.72 | 13.09 | 100.00 |
| FT | 36.71(−4.31) | 35.03(−5.83) | 4.34(−0.39) | 12.89(−0.20) | 99.55(−0.45) |
| SERAC | 91.91(50.89) | 80.61(39.75) | 6.55(1.83) | 48.81(35.72) | 100(0.00) |
| MEND | 95.93(54.91) | 74.24(33.38) | 2.56(−2.17) | 6.90(−6.19) | 96.08(−3.92) |
| Ext-Sub | 55.47(14.45) | 59.94(19.08) | 4.23(−0.50) | 15.56(2.47) | 97.71(−2.29) |
| IKE | 36.47(−4.55) | 25.78(−15.08) | 5.11(−0.39) | 12.33(−0.76) | 78.66(−21.34) |
| LLaMA2-7B | None | 33.68 | 34.16 | 7.44 | 40.42 | 100.00 |
| FT | 77.66(43.98) | 57.70(23.54) | 6.58(−0.86) | 39.78(−0.64) | 96.93(−3.07) |
| SERAC | 99.60(65.92) | 98.56(50.65) | 5.37(−2.08) | 31.05(−9.37) | 100(0.00) |
| MEND | 99.04(65.36) | 89.31(41.40) | 6.42(−1.02) | 21.71(−18.71) | 98.30(−1.70) |
| Ext-Sub | 67.92(34.24) | 68.56(20.65) | 7.95(−0.16) | 45.17(4.75) | 98.65(−1.35) |
| IKE | 38.31(4.63) | 33.84(−14.07) | 7.41(−0.03) | 41.90(1.48) | 84.77(−15.23) |
| LLaMA2-7B-Chat | None | 44.53 | 48.44 | 6.57 | 84.32 | 100 |
| FT | 79.89(35.36) | 58.70(10.26) | 7.18(0.61) | 85.24(0.92) | 96.00(−4.00) |
| SERAC | 99.60(55.07) | 98.56(50.65) | 5.37(−1.21) | 31.05(−53.27) | 100(0.00) |
| MEND | 94.41(49.88) | 75.42(27.51) | 6.94(0.37) | 76.94(−7.38) | 97.99(−2.01) |
| Ext-Sub | 61.29(16.76) | 62.17(14.26) | 7.53(0.96) | 84.78(0.46) | 97.92(−2.08) |
| IKE | 67.83(23.30) | 49.32(1.41) | 8.24(1.67) | 85.67(1.35) | 84.77(−15.23) |
| LLaMA2-13B-Chat | None | 47.91 | 50.43 | 7.39 | 81.79 | 100.00 |
| FT | 75.96(28.05) | 58.07(7.64) | 7.44(0.05) | 82.91(1.12) | 96.71(−3.29) |
| SERAC | 99.60(51.69) | 98.56(48.13) | 5.37(−2.02) | 31.05(−50.74) | 100.00(0.00) |
| MEND | 85.63(37.72) | 60.26(9.83) | 7.25(−0.14) | 81.17(−0.62) | 98.75(−1.25) |
| Ext-Sub | 73.18(25.27) | 73.02(22.59) | 7.52(0.14) | 81.92(0.13) | 99.08(−0.92) |
| IKE | 57.04(9.13) | 43.60(−6.83) | 8.75(1.37) | 51.84(−29.95) | 77.10(−22.90) |
)], 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/issn1000-1239.202330965, detailUrlEn=https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN/10.7544/issn1000-1239.202330965, pdfUrlCn=https://castjournals.cast.org.cn/joweb/jsjyjyfz/CN/PDF/10.7544/issn1000-1239.202330965, pdfUrlEn=https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN/PDF/10.7544/issn1000-1239.202330965, aliStartDate=0, aliEndDate=0, collectionFlag=false, citedCount=null, citedUrl=null, previewStatus=0, delFlag=0, hasFullText=1, orderTime=1714492800000, fullTextJson=null, articleText=null, reference=null)