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
刚刚
刚刚
Carrie完成签到,获得积分10
1秒前
敏感安柏发布了新的文献求助10
1秒前
1秒前
lijiaxin应助1177采纳,获得10
2秒前
打打应助科研通管家采纳,获得10
2秒前
大个应助科研通管家采纳,获得10
2秒前
科研通AI2S应助科研通管家采纳,获得10
2秒前
wanci应助科研通管家采纳,获得10
2秒前
丘比特应助科研通管家采纳,获得10
2秒前
科研通AI2S应助科研通管家采纳,获得10
2秒前
2秒前
2秒前
SYLH应助科研通管家采纳,获得10
2秒前
2秒前
2秒前
2秒前
慕青应助科研通管家采纳,获得10
2秒前
2秒前
武雨寒发布了新的文献求助10
3秒前
乐乐应助美好斓采纳,获得10
3秒前
4秒前
4秒前
lu完成签到,获得积分10
5秒前
IFCOCO完成签到,获得积分10
5秒前
四火发布了新的文献求助10
5秒前
wang完成签到,获得积分10
5秒前
李瑞康发布了新的文献求助10
6秒前
6秒前
babayaga发布了新的文献求助10
7秒前
呆萌冰绿完成签到,获得积分10
8秒前
零一发布了新的文献求助10
9秒前
小葡萄icon完成签到 ,获得积分10
9秒前
韩涵发布了新的文献求助10
9秒前
viviannne发布了新的文献求助10
9秒前
稀罕你发布了新的文献求助10
9秒前
10秒前
lhnsisi发布了新的文献求助10
10秒前
10秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
Picture Books with Same-sex Parented Families: Unintentional Censorship 700
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
Nucleophilic substitution in azasydnone-modified dinitroanisoles 500
不知道标题是什么 500
Indomethacinのヒトにおける経皮吸収 400
Effective Learning and Mental Wellbeing 400
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 3975871
求助须知:如何正确求助?哪些是违规求助? 3520207
关于积分的说明 11201502
捐赠科研通 3256611
什么是DOI,文献DOI怎么找? 1798403
邀请新用户注册赠送积分活动 877552
科研通“疑难数据库(出版商)”最低求助积分说明 806430