文献检索沙箱:为系统综述生成检索查询的大型语言模型。

IF 2.5 Q2 HEALTH CARE SCIENCES & SERVICES
JAMIA Open Pub Date : 2024-09-25 eCollection Date: 2024-10-01 DOI:10.1093/jamiaopen/ooae098
Gaelen P Adam, Jay DeYoung, Alice Paul, Ian J Saldanha, Ethan M Balk, Thomas A Trikalinos, Byron C Wallace
{"title":"文献检索沙箱:为系统综述生成检索查询的大型语言模型。","authors":"Gaelen P Adam, Jay DeYoung, Alice Paul, Ian J Saldanha, Ethan M Balk, Thomas A Trikalinos, Byron C Wallace","doi":"10.1093/jamiaopen/ooae098","DOIUrl":null,"url":null,"abstract":"<p><strong>Objectives: </strong>Development of search queries for systematic reviews (SRs) is time-consuming. In this work, we capitalize on recent advances in large language models (LLMs) and a relatively large dataset of natural language descriptions of reviews and corresponding Boolean searches to generate Boolean search queries from SR titles and key questions.</p><p><strong>Materials and methods: </strong>We curated a training dataset of 10 346 SR search queries registered in PROSPERO. We used this dataset to fine-tune a set of models to generate search queries based on Mistral-Instruct-7b. We evaluated the models quantitatively using an evaluation dataset of 57 SRs and qualitatively through semi-structured interviews with 8 experienced medical librarians.</p><p><strong>Results: </strong>The model-generated search queries had median sensitivity of 85% (interquartile range [IQR] 40%-100%) and number needed to read of 1206 citations (IQR 205-5810). The interviews suggested that the models lack both the necessary sensitivity and precision to be used without scrutiny but could be useful for topic scoping or as initial queries to be refined.</p><p><strong>Discussion: </strong>Future research should focus on improving the dataset with more high-quality search queries, assessing whether fine-tuning the model on other fields, such as the population and intervention, improves performance, and exploring the addition of interactivity to the interface.</p><p><strong>Conclusions: </strong>The datasets developed for this project can be used to train and evaluate LLMs that map review descriptions to Boolean search queries. The models cannot replace thoughtful search query design but may be useful in providing suggestions for key words and the framework for the query.</p>","PeriodicalId":36278,"journal":{"name":"JAMIA Open","volume":null,"pages":null},"PeriodicalIF":2.5000,"publicationDate":"2024-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11424077/pdf/","citationCount":"0","resultStr":"{\"title\":\"<i>Literature search sandbox</i>: a large language model that generates search queries for systematic reviews.\",\"authors\":\"Gaelen P Adam, Jay DeYoung, Alice Paul, Ian J Saldanha, Ethan M Balk, Thomas A Trikalinos, Byron C Wallace\",\"doi\":\"10.1093/jamiaopen/ooae098\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><strong>Objectives: </strong>Development of search queries for systematic reviews (SRs) is time-consuming. In this work, we capitalize on recent advances in large language models (LLMs) and a relatively large dataset of natural language descriptions of reviews and corresponding Boolean searches to generate Boolean search queries from SR titles and key questions.</p><p><strong>Materials and methods: </strong>We curated a training dataset of 10 346 SR search queries registered in PROSPERO. We used this dataset to fine-tune a set of models to generate search queries based on Mistral-Instruct-7b. We evaluated the models quantitatively using an evaluation dataset of 57 SRs and qualitatively through semi-structured interviews with 8 experienced medical librarians.</p><p><strong>Results: </strong>The model-generated search queries had median sensitivity of 85% (interquartile range [IQR] 40%-100%) and number needed to read of 1206 citations (IQR 205-5810). The interviews suggested that the models lack both the necessary sensitivity and precision to be used without scrutiny but could be useful for topic scoping or as initial queries to be refined.</p><p><strong>Discussion: </strong>Future research should focus on improving the dataset with more high-quality search queries, assessing whether fine-tuning the model on other fields, such as the population and intervention, improves performance, and exploring the addition of interactivity to the interface.</p><p><strong>Conclusions: </strong>The datasets developed for this project can be used to train and evaluate LLMs that map review descriptions to Boolean search queries. The models cannot replace thoughtful search query design but may be useful in providing suggestions for key words and the framework for the query.</p>\",\"PeriodicalId\":36278,\"journal\":{\"name\":\"JAMIA Open\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":2.5000,\"publicationDate\":\"2024-09-25\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11424077/pdf/\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"JAMIA Open\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1093/jamiaopen/ooae098\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"2024/10/1 0:00:00\",\"PubModel\":\"eCollection\",\"JCR\":\"Q2\",\"JCRName\":\"HEALTH CARE SCIENCES & SERVICES\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"JAMIA Open","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1093/jamiaopen/ooae098","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2024/10/1 0:00:00","PubModel":"eCollection","JCR":"Q2","JCRName":"HEALTH CARE SCIENCES & SERVICES","Score":null,"Total":0}
引用次数: 0

摘要

目的:开发系统性综述(SR)的搜索查询非常耗时。在这项工作中,我们利用最近在大型语言模型(LLMs)方面取得的进展以及一个相对较大的综述自然语言描述数据集和相应的布尔搜索,从系统综述标题和关键问题中生成布尔搜索查询:我们建立了一个训练数据集,其中包括在 PROSPERO 中登记的 10 346 条评论搜索查询。我们使用该数据集对一组模型进行微调,以便根据 Mistral-Instruct-7b 生成检索查询。我们使用 57 个 SR 的评估数据集对这些模型进行了定量评估,并通过与 8 位经验丰富的医学图书馆员进行半结构化访谈对这些模型进行了定性评估:结果:模型生成的检索查询的灵敏度中位数为 85%(四分位距 [IQR]为 40%-100%),需要阅读的引文数为 1206 条(IQR 为 205-5810)。访谈表明,这些模型缺乏必要的灵敏度和精确度,因此无需仔细审查即可使用,但对于主题范围界定或作为有待完善的初始查询可能有用:讨论:今后的研究应侧重于通过更多高质量的搜索查询来改进数据集,评估在人口和干预等其他领域对模型进行微调是否能提高性能,以及探索在界面中增加交互性:为本项目开发的数据集可用于训练和评估将综述描述映射到布尔搜索查询的 LLM。这些模型不能取代深思熟虑的搜索查询设计,但在提供关键词建议和查询框架方面可能会有所帮助。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Literature search sandbox: a large language model that generates search queries for systematic reviews.

Objectives: Development of search queries for systematic reviews (SRs) is time-consuming. In this work, we capitalize on recent advances in large language models (LLMs) and a relatively large dataset of natural language descriptions of reviews and corresponding Boolean searches to generate Boolean search queries from SR titles and key questions.

Materials and methods: We curated a training dataset of 10 346 SR search queries registered in PROSPERO. We used this dataset to fine-tune a set of models to generate search queries based on Mistral-Instruct-7b. We evaluated the models quantitatively using an evaluation dataset of 57 SRs and qualitatively through semi-structured interviews with 8 experienced medical librarians.

Results: The model-generated search queries had median sensitivity of 85% (interquartile range [IQR] 40%-100%) and number needed to read of 1206 citations (IQR 205-5810). The interviews suggested that the models lack both the necessary sensitivity and precision to be used without scrutiny but could be useful for topic scoping or as initial queries to be refined.

Discussion: Future research should focus on improving the dataset with more high-quality search queries, assessing whether fine-tuning the model on other fields, such as the population and intervention, improves performance, and exploring the addition of interactivity to the interface.

Conclusions: The datasets developed for this project can be used to train and evaluate LLMs that map review descriptions to Boolean search queries. The models cannot replace thoughtful search query design but may be useful in providing suggestions for key words and the framework for the query.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
JAMIA Open
JAMIA Open Medicine-Health Informatics
CiteScore
4.10
自引率
4.80%
发文量
102
审稿时长
16 weeks
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信