Article(id=1319726206489055947, tenantId=1146029695717560320, journalId=1263187385517883426, issueId=1319726164160139662, articleNumber=null, orderNo=null, doi=10.14062/j.issn.0454-5648.20240845, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1735747200000, receivedDateStr=2025-01-02, revisedDate=1737561600000, revisedDateStr=2025-01-23, acceptedDate=null, acceptedDateStr=null, onlineDate=1792576846953, onlineDateStr=2026-10-21, pubDate=1752940800000, pubDateStr=2025-07-20, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1792576846953, onlineIssueDateStr=2026-10-21, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1792576846953, creator=13701087609, updateTime=1792576846953, updator=13701087609, issue=Issue{id=1319726164160139662, tenantId=1146029695717560320, journalId=1263187385517883426, year='2025', volume='53', issue='7', pageStart='1777', pageEnd='2078', issueExtLink='null', onlineDate='null', pubDate='1752940800000', pubDateStr='2025-07-20', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1792576836862, creator='13701087609', updateTime=1792577335628, updator='13701087609', preIssue=null, nextIssue=null, articleTotal=null, ext={EN=IssueExt(id=1319728256174117458, tenantId=1146029695717560320, journalId=1263187385517883426, issueId=1319726164160139662, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1319728256174117459, tenantId=1146029695717560320, journalId=1263187385517883426, issueId=1319726164160139662, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null, downloadFileDto=null}, startPage=1844, endPage=1855, ext={EN=ArticleExt(id=1319726206740714188, articleId=1319726206489055947, tenantId=1146029695717560320, journalId=1263187385517883426, language=EN, title=Large Language Models Extract Synthesis Information of Lithium-ion Battery Solid-state Electrolytes from Literature, columnId=1322569937034527403, journalTitle=Journal of the Chinese Ceramic Society, columnName=Special Issue on Computation and Design of Electrochemical Energy Storage Materials—Research Article, runingTitle=null, highlight=null, articleAbstract=
Introduction

Lithium-ion batteries are widely used in electric vehicles due to their high energy density and environmental compatibility, but their safety and endurance are limited by liquid-state electrolytes. Solid-state electrolytes have attracted recent attention for their high safety and energy density, but their research faces some challenges. Artificial intelligence technologies, such as machine learning, can accelerate the discovery and optimization of solid-state electrolyte materials. However, extracting synthesis information from literature is time-consuming and prone to errors. Large language models (LLMs) become popular in the field of natural language processing. This paper was to propose the use of LLMs to automatically extract solid-state electrolyte synthesis information from literature via building datasets to train and fine-tune models.

Methods

The process of extracting synthesis information for solid-state electrolytes included five parts, i.e., literature downloading, parsing and processing, paragraph classification, information extraction, and synthesis process visualization. Initially, the downloaded XML documents were parsed to extract all paragraphs under the headings of "Experimental" or "Method". A classification dataset was constructed using these paragraphs, with the training set used to train and fine-tune a Bayesian model, a BERT model, and three different LLMs. The test set was used to evaluate the classification performance of different models. Three LLMs are fine-tuned using a dataset previously built for the extraction of synthesis information in inorganic catalysts, enabling them to complete the task of extracting synthesis information for solid-state electrolytes, outputting four parts of contents, i.e., product, raw materials, methods, and steps, and testing and evaluating with the synthesis paragraphs filtered by the classification models.

Results and discussion

The NB model slightly underperforms the other models in terms of precision, recall, and F1 score. This may be attributed to the pre-training of LLMs and BERT on extensive text data and their fine-tuning on paragraph classification data, endowing them with strong language comprehension abilities. The comparable overall performance of the 3B and 8B models may be attributed to the 3B model being derived from the 8B model through pruning and knowledge distillation, resulting in similar performance characteristics. The classification task in this paper is limited to the classification of solid-state electrolyte synthesis paragraphs and the training and testing data are relatively scarce, the superior performance of the 7B model does not imply that it is always superior to other models. The comparison between the 3B and 8B models demonstrates that in certain scenarios, smaller-parameter models can outperform their larger-parameter counterparts. Therefore, it is not always necessary to pursue models with more parameters. Instead, reasonable choices should be made based on the specific requirements of the task. In misclassifications, there is a higher incidence of predicting label 0 as 1, which may be due to the inclusion of descriptions of electrode preparation and battery assembly in paragraphs about non-solid electrolytes, involving the use of electrolytes, leading to the model to misjudge these paragraphs as solid-state electrolyte paragraphs. To further enhance the classification performance of LLMs, the way prompts the construction of the dataset that can be adjusted to allow LLMs to better understand the subtle differences between different paragraphs.

The three LLMs perform exceptionally well in the task of extracting synthesis information for solid-state electrolytes, demonstrating that the combination of pre-training and fine-tuning can fully leverage the text understanding and instruction following capabilities of large models, making them competent for the crucial task of extracting important information from the synthesis process of solid-state electrolytes. Moreover, the fine-tuning dataset used originates from the field of inorganic catalysts and shows excellent performance in the field of solid-state electrolytes, indicating a great generalization ability of large models. They learn the ability to extract structured information from unstructured text, rather than just extracting information about fixed materials and synthesis processes. The extraction effects of the 3B, 7B, and 8B models are comparable, indicating that the size of the model is not a sole factor determining performance. The design and training strategies of the models are equally important.

Conclusions

In the paragraph classification task, LLMs and BERT, benefiting from their pre-training on large-scale text data and fine-tuning for specific classification tasks, demonstrated classification performance that surpassed that of Bayesian models. Among the LLMs of different sizes, the 3B model, derived from the 8B model through pruning and knowledge distillation, showed similar classification effectiveness to the 8B model. The 7B model achieved an F1 score exceeding 0.9, thus highlighting its superior performance in handling such tasks.

In the synthesis information extraction task, LLMs were fine-tuned using a dataset of inorganic catalyst synthesis information. The results showed that the F1 scores of all three models exceeded 0.9, demonstrating great generalization capabilities of LLMs. This indicated that LLMs could learn the ability to extract structured information from unstructured text, rather than just extracting information about fixed materials and synthesis processes. The extraction performance of the 3B model was slightly better than that of the 7B and 8B models, thus indicating that the number of parameters could not be a sole factor determining performance. The design and training strategies of the models could be equally important.

, authors=Shihao WEI, Shuyuan LI, Yaxin WANG, Shaorui SUN, authorsList=Shihao WEI, Shuyuan LI, Yaxin WANG, Shaorui SUN, authorCompany=null, correspAuthors=Shaorui SUN, authorNote=

WEI Shihao (1999-), male, Master candidate. E-mail:

, correspAuthorsNote=
SUN Shaorui (1978-), male, Ph.D., Professor. E-mail:
, copyrightStatement=null, 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=1319726207441162957, articleId=1319726206489055947, tenantId=1146029695717560320, journalId=1263187385517883426, language=CN, title=大语言模型提取文献中锂离子电池固态电解质合成信息, columnId=1322569937340711596, journalTitle=硅酸盐学报, columnName=电化学储能材料计算与设计专题—研究论文, runingTitle=null, highlight=null, articleAbstract=

固态电解质是提升锂离子电池性能和安全性的关键材料,获取其结构化的合成信息对于相关研究至关重要。人工从文献中提取费时费力,基于规则的方法泛化性能差,机器学习的方法则需大量标记数据,都存在一定的局限性。本研究旨在利用大语言模型自动提取文献中的固态电解质合成信息。首先,训练段落分类模型,包括贝叶斯模型、BERT模型和3个不同的大语言模型,筛选出描述固态电解质合成过程的段落。然后,训练合成信息提取模型,为3个不同的大语言模型,从这些段落中提取合成信息。在段落分类任务中,Gemma模型的整体表现最好,F1分数超过0.9,LLaMA模型和BERT模型的表现次之,F1分数都超过0.85,贝叶斯模型的表现最差,F1分数低于0.85。在合成信息提取任务中,3个大语言模型的F1分数都超过了0.9。结果表明,大语言模型可以高效且准确地提取文献中锂离子电池固态电解质的合成信息,且小参数模型的性能与大参数模型相当。

, authors=韦士豪, 李舒远, 王亚鑫, 孙少瑞, authorsList=韦士豪, 李舒远, 王亚鑫, 孙少瑞, authorCompany=null, correspAuthors=孙少瑞, authorNote=

韦士豪(1999—),男,硕士研究生。

, correspAuthorsNote=
孙少瑞(1978—),男,博士,教授。
, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=HhgmuU+DYaNBRm9wARAyWQ==, magXml=LW9zKlGeKMAHFWGkkkO3Jg==, pdfUrl=null, pdf=XuNsFd3Eh0nK69EVlAjqwQ==, pdfFileSize=5900927, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=vm3Mb7ef/g49C7FJ7cg8gg==, mapNumber=null, fund=null)}, authors=[Author(id=1322569961688650036, tenantId=1146029695717560320, journalId=1263187385517883426, articleId=1319726206489055947, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=wsh228581@163.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322569961759953206, tenantId=1146029695717560320, journalId=1263187385517883426, articleId=1319726206489055947, authorId=1322569961688650036, language=EN, stringName=Shihao WEI, firstName=Shihao, middleName=null, lastName=WEI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=College of Materials Science and Engineering, Beijing University of Technology, Beijing 100124, China, bio={"content":"

WEI Shihao (1999-), male, Master candidate. E-mail:

"}, bioImg=null, bioContent=

WEI Shihao (1999-), male, Master candidate. E-mail:

, aboutCorrespAuthor=null), CN=AuthorExt(id=1322569961869005111, tenantId=1146029695717560320, journalId=1263187385517883426, articleId=1319726206489055947, authorId=1322569961688650036, language=CN, stringName=韦士豪, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=北京工业大学材料科学与工程学院,北京 100124, bio={"content":"

韦士豪(1999—),男,硕士研究生。

"}, bioImg=null, bioContent=

韦士豪(1999—),男,硕士研究生。

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322569961608958256, tenantId=1146029695717560320, journalId=1263187385517883426, articleId=1319726206489055947, xref=null, ext=[AuthorCompanyExt(id=1322569961617346865, tenantId=1146029695717560320, journalId=1263187385517883426, articleId=1319726206489055947, companyId=1322569961608958256, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=College of Materials Science and Engineering, Beijing University of Technology, Beijing 100124, China), AuthorCompanyExt(id=1322569961625735474, tenantId=1146029695717560320, journalId=1263187385517883426, articleId=1319726206489055947, companyId=1322569961608958256, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=北京工业大学材料科学与工程学院,北京 100124)])]), Author(id=1322569961940308281, tenantId=1146029695717560320, journalId=1263187385517883426, articleId=1319726206489055947, 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=1322569962011611451, tenantId=1146029695717560320, journalId=1263187385517883426, articleId=1319726206489055947, authorId=1322569961940308281, language=EN, stringName=Shuyuan LI, firstName=Shuyuan, middleName=null, lastName=LI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=College of Materials Science and Engineering, Beijing University of Technology, Beijing 100124, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322569962082914620, tenantId=1146029695717560320, journalId=1263187385517883426, articleId=1319726206489055947, authorId=1322569961940308281, language=CN, stringName=李舒远, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=北京工业大学材料科学与工程学院,北京 100124, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322569961608958256, tenantId=1146029695717560320, journalId=1263187385517883426, articleId=1319726206489055947, xref=null, ext=[AuthorCompanyExt(id=1322569961617346865, tenantId=1146029695717560320, journalId=1263187385517883426, articleId=1319726206489055947, companyId=1322569961608958256, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=College of Materials Science and Engineering, Beijing University of Technology, Beijing 100124, China), AuthorCompanyExt(id=1322569961625735474, tenantId=1146029695717560320, journalId=1263187385517883426, articleId=1319726206489055947, companyId=1322569961608958256, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=北京工业大学材料科学与工程学院,北京 100124)])]), Author(id=1322569962158412094, tenantId=1146029695717560320, journalId=1263187385517883426, articleId=1319726206489055947, 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=1322569962263269696, tenantId=1146029695717560320, journalId=1263187385517883426, articleId=1319726206489055947, authorId=1322569962158412094, language=EN, stringName=Yaxin WANG, firstName=Yaxin, middleName=null, lastName=WANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=College of Materials Science and Engineering, Beijing University of Technology, Beijing 100124, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322569962351350081, tenantId=1146029695717560320, journalId=1263187385517883426, articleId=1319726206489055947, authorId=1322569962158412094, language=CN, stringName=王亚鑫, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=北京工业大学材料科学与工程学院,北京 100124, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322569961608958256, tenantId=1146029695717560320, journalId=1263187385517883426, articleId=1319726206489055947, xref=null, ext=[AuthorCompanyExt(id=1322569961617346865, tenantId=1146029695717560320, journalId=1263187385517883426, articleId=1319726206489055947, companyId=1322569961608958256, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=College of Materials Science and Engineering, Beijing University of Technology, Beijing 100124, China), AuthorCompanyExt(id=1322569961625735474, tenantId=1146029695717560320, journalId=1263187385517883426, articleId=1319726206489055947, companyId=1322569961608958256, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=北京工业大学材料科学与工程学院,北京 100124)])]), Author(id=1322569962439430467, tenantId=1146029695717560320, journalId=1263187385517883426, articleId=1319726206489055947, orderNo=3, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=sunsr@bjut.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1322569962544288069, tenantId=1146029695717560320, journalId=1263187385517883426, articleId=1319726206489055947, authorId=1322569962439430467, language=EN, stringName=Shaorui SUN, firstName=Shaorui, middleName=null, lastName=SUN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=College of Materials Science and Engineering, Beijing University of Technology, Beijing 100124, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322569962615591238, tenantId=1146029695717560320, journalId=1263187385517883426, articleId=1319726206489055947, authorId=1322569962439430467, language=CN, stringName=孙少瑞, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=北京工业大学材料科学与工程学院,北京 100124, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322569961608958256, tenantId=1146029695717560320, journalId=1263187385517883426, articleId=1319726206489055947, xref=null, ext=[AuthorCompanyExt(id=1322569961617346865, tenantId=1146029695717560320, journalId=1263187385517883426, articleId=1319726206489055947, companyId=1322569961608958256, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=College of Materials Science and Engineering, Beijing University of Technology, Beijing 100124, China), AuthorCompanyExt(id=1322569961625735474, tenantId=1146029695717560320, journalId=1263187385517883426, articleId=1319726206489055947, companyId=1322569961608958256, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=北京工业大学材料科学与工程学院,北京 100124)])])], keywords=[Keyword(id=1322569962774974791, tenantId=1146029695717560320, journalId=1263187385517883426, articleId=1319726206489055947, language=EN, orderNo=1, keyword=large language models), Keyword(id=1322569962846277960, tenantId=1146029695717560320, journalId=1263187385517883426, articleId=1319726206489055947, language=EN, orderNo=2, keyword=lithium-ion batteries), Keyword(id=1322569962917581129, tenantId=1146029695717560320, journalId=1263187385517883426, articleId=1319726206489055947, language=EN, orderNo=3, keyword=solid-state electrolytes), Keyword(id=1322569963001467210, tenantId=1146029695717560320, journalId=1263187385517883426, articleId=1319726206489055947, language=EN, orderNo=4, keyword=extraction), Keyword(id=1322569963068576075, tenantId=1146029695717560320, journalId=1263187385517883426, articleId=1319726206489055947, language=CN, orderNo=1, keyword=大语言模型), Keyword(id=1322569963186016588, tenantId=1146029695717560320, journalId=1263187385517883426, articleId=1319726206489055947, language=CN, orderNo=2, keyword=锂离子电池), Keyword(id=1322569963248931149, tenantId=1146029695717560320, journalId=1263187385517883426, articleId=1319726206489055947, language=CN, orderNo=3, keyword=固态电解质), Keyword(id=1322569963299262798, tenantId=1146029695717560320, journalId=1263187385517883426, articleId=1319726206489055947, language=CN, orderNo=4, keyword=提取)], refs=null, funds=[Fund(id=1322569963420897615, tenantId=1146029695717560320, journalId=1263187385517883426, articleId=1319726206489055947, awardId=2021YFA1201000, language=CN, fundingSource=国家科技重大专项资助项目(2021YFA1201000), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1322569961608958256, tenantId=1146029695717560320, journalId=1263187385517883426, articleId=1319726206489055947, xref=null, ext=[AuthorCompanyExt(id=1322569961617346865, tenantId=1146029695717560320, journalId=1263187385517883426, articleId=1319726206489055947, companyId=1322569961608958256, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=College of Materials Science and Engineering, Beijing University of Technology, Beijing 100124, China), AuthorCompanyExt(id=1322569961625735474, tenantId=1146029695717560320, journalId=1263187385517883426, articleId=1319726206489055947, companyId=1322569961608958256, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=北京工业大学材料科学与工程学院,北京 100124)])], figs=null, attaches=null, journal=Journal(id=1263186332462366751, delFlag=0, nameCn=硅酸盐学报, nameEn=Journal of the Chinese Ceramic Society, nameHistory1=null, nameHistory2=null, issn=0454-5648, eissn=null, cn=11-2310/TQ, 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=8Qg1+Is+LeRD1Lv6UJcXRg==, journalPrice=null, startedYear=null, abbrevIsoEn=Journal of the Chinese Ceramic Society, journalRemark=null, publicationField=null, createdTime=1779096690528, updatedTime=1788951192520, createdBy=18614031015, updatedBy=13041195026, firstLetterCn=G, firstLetterEn=G, subjectCode=Engineering, subjectName=null, subjectCodeEn=Engineering, subjectNameEn=null, picCn=8Qg1+Is+LeRD1Lv6UJcXRg==, picEn=AY9tl+TwuKtB81GF+w4WAg==, jcr=null, cjcr=null, exts=[JournalExt(id=1304519110767960749, language=CN, name=硅酸盐学报, 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=1788951192800, updatedTime=1788951192800, createdBy=13041195026, updatedBy=13041195026, submissionGuidelinesUrl=, submissionAuthorUrl=https://gxyb.cbpt.cnki.net/index.aspx?t=1, submissionEditorUrl=https://gxyb.cbpt.cnki.net/index.aspx?t=3, submissionReviewUrl=https://gxyb.cbpt.cnki.net/index.aspx?t=2, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1304519110839263918, language=EN, name=Journal of the Chinese Ceramic Society, 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=1788951192817, updatedTime=1788951192817, createdBy=13041195026, updatedBy=13041195026, submissionGuidelinesUrl=, submissionAuthorUrl=https://gxyb.cbpt.cnki.net/index.aspx?t=1, submissionEditorUrl=https://gxyb.cbpt.cnki.net/index.aspx?t=3, submissionReviewUrl=https://gxyb.cbpt.cnki.net/index.aspx?t=2, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1263187385517883426, websiteList=[Website(id=1263188159895093557, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1263187385517883426, 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/gsyxb/CN, language=CN, createTime=1779097126220, createBy=18614031015, updateTime=1779097837121, updateBy=18614031015, name=硅酸盐学报-中文, tplId=1146099689490845704, title=硅酸盐学报, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1263191261578649862, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1263188159895093557, code=articleTextType, value=kx, createTime=1779097865719, updateTime=1779097865719, creator=18614031015, updator=18614031015), WebsiteProps(id=1263191261545095427, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1263188159895093557, code=banner, value=null, createTime=1779097865711, updateTime=1779097865711, creator=18614031015, updator=18614031015), WebsiteProps(id=1263191261599621385, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1263188159895093557, code=grayFlag, value=0, createTime=1779097865724, updateTime=1779097865724, creator=18614031015, updator=18614031015), WebsiteProps(id=1263191261532512514, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1263188159895093557, code=logo, value=https://castjournals.cast.org.cn/joweb/gsyxb/CN/file/pic?fileId=Oqq9gXZG0JiYeHvLNwX/eg==, createTime=1779097865708, updateTime=1779097865708, creator=18614031015, updator=18614031015), WebsiteProps(id=1263191261620592907, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1263188159895093557, code=minRunFlag, value=0, createTime=1779097865729, updateTime=1779097865729, creator=18614031015, updator=18614031015), WebsiteProps(id=1263191261574455557, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1263188159895093557, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/gsyxb/CN/file/pic, createTime=1779097865718, updateTime=1779097865718, creator=18614031015, updator=18614031015), WebsiteProps(id=1263191261616398602, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1263188159895093557, code=silenceFlag, value=0, createTime=1779097865728, updateTime=1779097865728, creator=18614031015, updator=18614031015), WebsiteProps(id=1263191261566066948, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1263188159895093557, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1779097865716, updateTime=1779097865716, creator=18614031015, updator=18614031015), WebsiteProps(id=1263191261587038471, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1263188159895093557, code=themeColor, value=null, createTime=1779097865721, updateTime=1779097865721, creator=18614031015, updator=18614031015), WebsiteProps(id=1263191261591232776, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1263188159895093557, code=themeStyle, value=null, createTime=1779097865722, updateTime=1779097865722, creator=18614031015, updator=18614031015)]), Website(id=1263188160188694841, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1263187385517883426, 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/gsyxb/EN, language=EN, createTime=1779097126348, createBy=18614031015, updateTime=1779097825280, updateBy=18614031015, name=硅酸盐学报-英文, tplId=1146101810881728533, title=Journal of the Chinese Ceramic Society, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1263191231102836987, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1263188160188694841, code=articleTextType, value=kx, createTime=1779097858453, updateTime=1779097858453, creator=18614031015, updator=18614031015), WebsiteProps(id=1263191231052505336, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1263188160188694841, code=banner, value=null, createTime=1779097858441, updateTime=1779097858441, creator=18614031015, updator=18614031015), WebsiteProps(id=1263191231186723070, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1263188160188694841, code=grayFlag, value=0, createTime=1779097858473, updateTime=1779097858473, creator=18614031015, updator=18614031015), WebsiteProps(id=1263191231039922423, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1263188160188694841, code=logo, value=https://castjournals.cast.org.cn/joweb/gsyxb/EN/file/pic?fileId=Oqq9gXZG0JiYeHvLNwX/eg==, createTime=1779097858438, updateTime=1779097858438, creator=18614031015, updator=18614031015), WebsiteProps(id=1263191231358689536, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1263188160188694841, code=minRunFlag, value=0, createTime=1779097858514, updateTime=1779097858514, creator=18614031015, updator=18614031015), WebsiteProps(id=1263191231094448378, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1263188160188694841, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/gsyxb/EN/file/pic, createTime=1779097858451, updateTime=1779097858451, creator=18614031015, updator=18614031015), WebsiteProps(id=1263191231195111679, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1263188160188694841, code=silenceFlag, value=0, createTime=1779097858475, updateTime=1779097858475, creator=18614031015, updator=18614031015), WebsiteProps(id=1263191231086059769, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1263188160188694841, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_en_623/, createTime=1779097858449, updateTime=1779097858449, creator=18614031015, updator=18614031015), WebsiteProps(id=1263191231111225596, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1263188160188694841, code=themeColor, value=null, createTime=1779097858455, updateTime=1779097858455, creator=18614031015, updator=18614031015), WebsiteProps(id=1263191231144780029, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1263188160188694841, code=themeStyle, value=null, createTime=1779097858463, updateTime=1779097858463, creator=18614031015, updator=18614031015)])], journalTitle=硅酸盐学报, weixinUrl=null, journalUrl=https://jccsoc.cbpt.cnki.net/, iacademicId=null, status=1, seqNo=null, journalTitleEn=Journal of the Chinese Ceramic Society, journalPhotoCn=8Qg1+Is+LeRD1Lv6UJcXRg==, journalPhotoEn=AY9tl+TwuKtB81GF+w4WAg==, journalFirstLetter=G, 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/gsyxb/CN/10.14062/j.issn.0454-5648.20240845, detailUrlEn=https://castjournals.cast.org.cn/joweb/gsyxb/EN/10.14062/j.issn.0454-5648.20240845, pdfUrlCn=https://castjournals.cast.org.cn/joweb/gsyxb/CN/PDF/10.14062/j.issn.0454-5648.20240845, pdfUrlEn=https://castjournals.cast.org.cn/joweb/gsyxb/EN/PDF/10.14062/j.issn.0454-5648.20240845, aliStartDate=0, aliEndDate=0, collectionFlag=false, citedCount=null, citedUrl=null, previewStatus=0, delFlag=0, hasFullText=0, orderTime=1752940800000, fullTextJson=null, articleText=null, reference=null)
收藏切换
大语言模型提取文献中锂离子电池固态电解质合成信息
收藏切换
PDF下载
韦士豪 , 李舒远 , 王亚鑫 , 孙少瑞
硅酸盐学报 | 电化学储能材料计算与设计专题—研究论文 2025,53(7): 1844-1855
收起
收藏切换
硅酸盐学报 |电化学储能材料计算与设计专题—研究论文 2025 , 53 (7) : 1844 -1855
大语言模型提取文献中锂离子电池固态电解质合成信息
全屏
[Author(id=1322569961688650036, tenantId=1146029695717560320, journalId=1263187385517883426, articleId=1319726206489055947, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=wsh228581@163.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322569961759953206, tenantId=1146029695717560320, journalId=1263187385517883426, articleId=1319726206489055947, authorId=1322569961688650036, language=EN, stringName=Shihao WEI, firstName=Shihao, middleName=null, lastName=WEI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=College of Materials Science and Engineering, Beijing University of Technology, Beijing 100124, China, bio={"content":"

WEI Shihao (1999-), male, Master candidate. E-mail:

"}, bioImg=null, bioContent=

WEI Shihao (1999-), male, Master candidate. E-mail:

, aboutCorrespAuthor=null), CN=AuthorExt(id=1322569961869005111, tenantId=1146029695717560320, journalId=1263187385517883426, articleId=1319726206489055947, authorId=1322569961688650036, language=CN, stringName=韦士豪, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=北京工业大学材料科学与工程学院,北京 100124, bio={"content":"

韦士豪(1999—),男,硕士研究生。

"}, bioImg=null, bioContent=

韦士豪(1999—),男,硕士研究生。

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322569961608958256, tenantId=1146029695717560320, journalId=1263187385517883426, articleId=1319726206489055947, xref=null, ext=[AuthorCompanyExt(id=1322569961617346865, tenantId=1146029695717560320, journalId=1263187385517883426, articleId=1319726206489055947, companyId=1322569961608958256, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=College of Materials Science and Engineering, Beijing University of Technology, Beijing 100124, China), AuthorCompanyExt(id=1322569961625735474, tenantId=1146029695717560320, journalId=1263187385517883426, articleId=1319726206489055947, companyId=1322569961608958256, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=北京工业大学材料科学与工程学院,北京 100124)])]), Author(id=1322569961940308281, tenantId=1146029695717560320, journalId=1263187385517883426, articleId=1319726206489055947, 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=1322569962011611451, tenantId=1146029695717560320, journalId=1263187385517883426, articleId=1319726206489055947, authorId=1322569961940308281, language=EN, stringName=Shuyuan LI, firstName=Shuyuan, middleName=null, lastName=LI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=College of Materials Science and Engineering, Beijing University of Technology, Beijing 100124, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322569962082914620, tenantId=1146029695717560320, journalId=1263187385517883426, articleId=1319726206489055947, authorId=1322569961940308281, language=CN, stringName=李舒远, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=北京工业大学材料科学与工程学院,北京 100124, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322569961608958256, tenantId=1146029695717560320, journalId=1263187385517883426, articleId=1319726206489055947, xref=null, ext=[AuthorCompanyExt(id=1322569961617346865, tenantId=1146029695717560320, journalId=1263187385517883426, articleId=1319726206489055947, companyId=1322569961608958256, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=College of Materials Science and Engineering, Beijing University of Technology, Beijing 100124, China), AuthorCompanyExt(id=1322569961625735474, tenantId=1146029695717560320, journalId=1263187385517883426, articleId=1319726206489055947, companyId=1322569961608958256, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=北京工业大学材料科学与工程学院,北京 100124)])]), Author(id=1322569962158412094, tenantId=1146029695717560320, journalId=1263187385517883426, articleId=1319726206489055947, 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=1322569962263269696, tenantId=1146029695717560320, journalId=1263187385517883426, articleId=1319726206489055947, authorId=1322569962158412094, language=EN, stringName=Yaxin WANG, firstName=Yaxin, middleName=null, lastName=WANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=College of Materials Science and Engineering, Beijing University of Technology, Beijing 100124, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322569962351350081, tenantId=1146029695717560320, journalId=1263187385517883426, articleId=1319726206489055947, authorId=1322569962158412094, language=CN, stringName=王亚鑫, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=北京工业大学材料科学与工程学院,北京 100124, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322569961608958256, tenantId=1146029695717560320, journalId=1263187385517883426, articleId=1319726206489055947, xref=null, ext=[AuthorCompanyExt(id=1322569961617346865, tenantId=1146029695717560320, journalId=1263187385517883426, articleId=1319726206489055947, companyId=1322569961608958256, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=College of Materials Science and Engineering, Beijing University of Technology, Beijing 100124, China), AuthorCompanyExt(id=1322569961625735474, tenantId=1146029695717560320, journalId=1263187385517883426, articleId=1319726206489055947, companyId=1322569961608958256, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=北京工业大学材料科学与工程学院,北京 100124)])]), Author(id=1322569962439430467, tenantId=1146029695717560320, journalId=1263187385517883426, articleId=1319726206489055947, orderNo=3, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=sunsr@bjut.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1322569962544288069, tenantId=1146029695717560320, journalId=1263187385517883426, articleId=1319726206489055947, authorId=1322569962439430467, language=EN, stringName=Shaorui SUN, firstName=Shaorui, middleName=null, lastName=SUN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=College of Materials Science and Engineering, Beijing University of Technology, Beijing 100124, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322569962615591238, tenantId=1146029695717560320, journalId=1263187385517883426, articleId=1319726206489055947, authorId=1322569962439430467, language=CN, stringName=孙少瑞, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=北京工业大学材料科学与工程学院,北京 100124, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322569961608958256, tenantId=1146029695717560320, journalId=1263187385517883426, articleId=1319726206489055947, xref=null, ext=[AuthorCompanyExt(id=1322569961617346865, tenantId=1146029695717560320, journalId=1263187385517883426, articleId=1319726206489055947, companyId=1322569961608958256, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=College of Materials Science and Engineering, Beijing University of Technology, Beijing 100124, China), AuthorCompanyExt(id=1322569961625735474, tenantId=1146029695717560320, journalId=1263187385517883426, articleId=1319726206489055947, companyId=1322569961608958256, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=北京工业大学材料科学与工程学院,北京 100124)])])]
韦士豪 , 李舒远, 王亚鑫, 孙少瑞
作者信息
  • 北京工业大学材料科学与工程学院,北京 100124
通讯作者:
孙少瑞(1978—),男,博士,教授。
作者简介:

韦士豪(1999—),男,硕士研究生。

Large Language Models Extract Synthesis Information of Lithium-ion Battery Solid-state Electrolytes from Literature
Shihao WEI , Shuyuan LI, Yaxin WANG, Shaorui SUN
Affiliations
  • College of Materials Science and Engineering, Beijing University of Technology, Beijing 100124, China
  • Corresponding Author:
    SUN Shaorui (1978-), male, Ph.D., Professor. E-mail:

    WEI Shihao (1999-), male, Master candidate. E-mail:

出版时间: 2025-07-20 doi: 10.14062/j.issn.0454-5648.20240845
文章导航
收藏切换

固态电解质是提升锂离子电池性能和安全性的关键材料,获取其结构化的合成信息对于相关研究至关重要。人工从文献中提取费时费力,基于规则的方法泛化性能差,机器学习的方法则需大量标记数据,都存在一定的局限性。本研究旨在利用大语言模型自动提取文献中的固态电解质合成信息。首先,训练段落分类模型,包括贝叶斯模型、BERT模型和3个不同的大语言模型,筛选出描述固态电解质合成过程的段落。然后,训练合成信息提取模型,为3个不同的大语言模型,从这些段落中提取合成信息。在段落分类任务中,Gemma模型的整体表现最好,F1分数超过0.9,LLaMA模型和BERT模型的表现次之,F1分数都超过0.85,贝叶斯模型的表现最差,F1分数低于0.85。在合成信息提取任务中,3个大语言模型的F1分数都超过了0.9。结果表明,大语言模型可以高效且准确地提取文献中锂离子电池固态电解质的合成信息,且小参数模型的性能与大参数模型相当。

大语言模型  /  锂离子电池  /  固态电解质  /  提取
Introduction

Lithium-ion batteries are widely used in electric vehicles due to their high energy density and environmental compatibility, but their safety and endurance are limited by liquid-state electrolytes. Solid-state electrolytes have attracted recent attention for their high safety and energy density, but their research faces some challenges. Artificial intelligence technologies, such as machine learning, can accelerate the discovery and optimization of solid-state electrolyte materials. However, extracting synthesis information from literature is time-consuming and prone to errors. Large language models (LLMs) become popular in the field of natural language processing. This paper was to propose the use of LLMs to automatically extract solid-state electrolyte synthesis information from literature via building datasets to train and fine-tune models.

Methods

The process of extracting synthesis information for solid-state electrolytes included five parts, i.e., literature downloading, parsing and processing, paragraph classification, information extraction, and synthesis process visualization. Initially, the downloaded XML documents were parsed to extract all paragraphs under the headings of "Experimental" or "Method". A classification dataset was constructed using these paragraphs, with the training set used to train and fine-tune a Bayesian model, a BERT model, and three different LLMs. The test set was used to evaluate the classification performance of different models. Three LLMs are fine-tuned using a dataset previously built for the extraction of synthesis information in inorganic catalysts, enabling them to complete the task of extracting synthesis information for solid-state electrolytes, outputting four parts of contents, i.e., product, raw materials, methods, and steps, and testing and evaluating with the synthesis paragraphs filtered by the classification models.

Results and discussion

The NB model slightly underperforms the other models in terms of precision, recall, and F1 score. This may be attributed to the pre-training of LLMs and BERT on extensive text data and their fine-tuning on paragraph classification data, endowing them with strong language comprehension abilities. The comparable overall performance of the 3B and 8B models may be attributed to the 3B model being derived from the 8B model through pruning and knowledge distillation, resulting in similar performance characteristics. The classification task in this paper is limited to the classification of solid-state electrolyte synthesis paragraphs and the training and testing data are relatively scarce, the superior performance of the 7B model does not imply that it is always superior to other models. The comparison between the 3B and 8B models demonstrates that in certain scenarios, smaller-parameter models can outperform their larger-parameter counterparts. Therefore, it is not always necessary to pursue models with more parameters. Instead, reasonable choices should be made based on the specific requirements of the task. In misclassifications, there is a higher incidence of predicting label 0 as 1, which may be due to the inclusion of descriptions of electrode preparation and battery assembly in paragraphs about non-solid electrolytes, involving the use of electrolytes, leading to the model to misjudge these paragraphs as solid-state electrolyte paragraphs. To further enhance the classification performance of LLMs, the way prompts the construction of the dataset that can be adjusted to allow LLMs to better understand the subtle differences between different paragraphs.

The three LLMs perform exceptionally well in the task of extracting synthesis information for solid-state electrolytes, demonstrating that the combination of pre-training and fine-tuning can fully leverage the text understanding and instruction following capabilities of large models, making them competent for the crucial task of extracting important information from the synthesis process of solid-state electrolytes. Moreover, the fine-tuning dataset used originates from the field of inorganic catalysts and shows excellent performance in the field of solid-state electrolytes, indicating a great generalization ability of large models. They learn the ability to extract structured information from unstructured text, rather than just extracting information about fixed materials and synthesis processes. The extraction effects of the 3B, 7B, and 8B models are comparable, indicating that the size of the model is not a sole factor determining performance. The design and training strategies of the models are equally important.

Conclusions

In the paragraph classification task, LLMs and BERT, benefiting from their pre-training on large-scale text data and fine-tuning for specific classification tasks, demonstrated classification performance that surpassed that of Bayesian models. Among the LLMs of different sizes, the 3B model, derived from the 8B model through pruning and knowledge distillation, showed similar classification effectiveness to the 8B model. The 7B model achieved an F1 score exceeding 0.9, thus highlighting its superior performance in handling such tasks.

In the synthesis information extraction task, LLMs were fine-tuned using a dataset of inorganic catalyst synthesis information. The results showed that the F1 scores of all three models exceeded 0.9, demonstrating great generalization capabilities of LLMs. This indicated that LLMs could learn the ability to extract structured information from unstructured text, rather than just extracting information about fixed materials and synthesis processes. The extraction performance of the 3B model was slightly better than that of the 7B and 8B models, thus indicating that the number of parameters could not be a sole factor determining performance. The design and training strategies of the models could be equally important.

large language models  /  lithium-ion batteries  /  solid-state electrolytes  /  extraction
韦士豪, 李舒远, 王亚鑫, 孙少瑞. 大语言模型提取文献中锂离子电池固态电解质合成信息. 硅酸盐学报, 2025 , 53 (7) : 1844 -1855 . DOI: 10.14062/j.issn.0454-5648.20240845
Shihao WEI, Shuyuan LI, Yaxin WANG, Shaorui SUN. Large Language Models Extract Synthesis Information of Lithium-ion Battery Solid-state Electrolytes from Literature[J]. Journal of the Chinese Ceramic Society, 2025 , 53 (7) : 1844 -1855 . DOI: 10.14062/j.issn.0454-5648.20240845
  • 国家科技重大专项资助项目(2021YFA1201000)
参考文献 引证文献
排序方式:
2025年第53卷第7期
PDF下载
54
13
引用本文
BibTeX
文章信息
doi: 10.14062/j.issn.0454-5648.20240845
  • 接收时间:2025-01-02
  • 首发时间:2026-10-21
  • 出版时间:2025-07-20
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2025-01-02
  • 修回日期:2025-01-23
基金
国家科技重大专项资助项目(2021YFA1201000)
作者信息
    北京工业大学材料科学与工程学院,北京 100124

通讯作者:

孙少瑞(1978—),男,博士,教授。
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/gsyxb/CN/10.14062/j.issn.0454-5648.20240845
分享至
全文二维码

扫描看全文

引用本文
BibTeX
本文的引用情况
2种不同金属材料的力学参数
科
Family
属数
Number of
genus
种数
Number of
species
占总种数比例
Percentage of
total species (%)
属
Genus
种数
Number of
species
占总种数比例
Percentage of total
species (%)
鹅膏菌科Amanitaceae 2 11 5.26 鹅膏菌属 Amanita 10 4.78
小菇科 Mycenaceae 2 12 5.74 丝盖伞属 Inocybe 5 2.39
多孔菌科 Polyporaceae 8 14 6.70 蜡蘑属 Laccaria 5 2.39
红菇科 Russulaceae 3 23 11.00 小皮伞属 Marasmius 6 2.87
小菇属 Mycena 11 5.26
光柄菇属 Pluteus 5 2.39
红菇属 Russula 17 8.13
栓菌属 Trametes 5 2.39
关闭全屏