Performance of two large language models for data extraction in evidence synthesis

计算机科学 解析 数据提取 上传 范围(计算机科学) 插件 数据挖掘 自然语言处理 数据科学 梅德林 万维网 程序设计语言 政治学 法学
作者
Amanda Konet,Ian B. Thomas,Gerald Gartlehner,Leila C. Kahwati,Rainer Hilscher,Shannon Kugley,Karen Crotty,Meera Viswanathan,Rob Chew
出处
期刊:Research Synthesis Methods [Wiley]
卷期号:15 (5): 818-824 被引量:11
标识
DOI:10.1002/jrsm.1732
摘要

Abstract Accurate data extraction is a key component of evidence synthesis and critical to valid results. The advent of publicly available large language models (LLMs) has generated interest in these tools for evidence synthesis and created uncertainty about the choice of LLM. We compare the performance of two widely available LLMs (Claude 2 and GPT‐4) for extracting pre‐specified data elements from 10 published articles included in a previously completed systematic review. We use prompts and full study PDFs to compare the outputs from the browser versions of Claude 2 and GPT‐4. GPT‐4 required use of a third‐party plugin to upload and parse PDFs. Accuracy was high for Claude 2 (96.3%). The accuracy of GPT‐4 with the plug‐in was lower (68.8%); however, most of the errors were due to the plug‐in. Both LLMs correctly recognized when prespecified data elements were missing from the source PDF and generated correct information for data elements that were not reported explicitly in the articles. A secondary analysis demonstrated that, when provided selected text from the PDFs, Claude 2 and GPT‐4 accurately extracted 98.7% and 100% of the data elements, respectively. Limitations include the narrow scope of the study PDFs used, that prompt development was completed using only Claude 2, and that we cannot guarantee the open‐source articles were not used to train the LLMs. This study highlights the potential for LLMs to revolutionize data extraction but underscores the importance of accurate PDF parsing. For now, it remains essential for a human investigator to validate LLM extractions.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
MS903完成签到,获得积分10
3秒前
CJW完成签到 ,获得积分10
4秒前
韧迹完成签到 ,获得积分0
4秒前
mmd完成签到 ,获得积分10
4秒前
七一安完成签到 ,获得积分10
5秒前
浪麻麻完成签到 ,获得积分10
9秒前
包容的剑完成签到 ,获得积分10
13秒前
等待的大炮完成签到,获得积分10
13秒前
注水萝卜完成签到 ,获得积分10
15秒前
Chem34完成签到,获得积分10
23秒前
25秒前
量子星尘发布了新的文献求助10
25秒前
hhh2018687完成签到,获得积分10
25秒前
25秒前
26秒前
26秒前
26秒前
26秒前
27秒前
27秒前
27秒前
27秒前
27秒前
27秒前
27秒前
嘒彼小星完成签到 ,获得积分10
27秒前
27秒前
28秒前
28秒前
28秒前
28秒前
29秒前
ri_290完成签到,获得积分10
29秒前
30秒前
nsc发布了新的文献求助30
32秒前
nsc发布了新的文献求助10
32秒前
nsc发布了新的文献求助10
32秒前
nsc发布了新的文献求助10
32秒前
nsc发布了新的文献求助10
32秒前
nsc发布了新的文献求助10
32秒前
高分求助中
【提示信息,请勿应助】关于scihub 10000
Les Mantodea de Guyane: Insecta, Polyneoptera [The Mantids of French Guiana] 3000
徐淮辽南地区新元古代叠层石及生物地层 3000
The Mother of All Tableaux: Order, Equivalence, and Geometry in the Large-scale Structure of Optimality Theory 3000
Handbook of Industrial Diamonds.Vol2 1100
Global Eyelash Assessment scale (GEA) 1000
Picture Books with Same-sex Parented Families: Unintentional Censorship 550
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 4038039
求助须知:如何正确求助?哪些是违规求助? 3575756
关于积分的说明 11373782
捐赠科研通 3305574
什么是DOI,文献DOI怎么找? 1819239
邀请新用户注册赠送积分活动 892655
科研通“疑难数据库(出版商)”最低求助积分说明 815022