Can large language models replace humans in systematic reviews? Evaluating GPT‐4's efficacy in screening and extracting data from peer‐reviewed and grey literature in multiple languages

Author:

Khraisha Qusai12ORCID,Put Sophie3,Kappenberg Johanna2,Warraitch Azza12,Hadfield Kristin12ORCID

Affiliation:

1. Trinity Centre for Global Health Trinity College Dublin Dublin Ireland

2. School of Psychology Trinity College Dublin Dublin Ireland

3. Department of Education York University York UK

Abstract

AbstractSystematic reviews are vital for guiding practice, research and policy, although they are often slow and labour‐intensive. Large language models (LLMs) could speed up and automate systematic reviews, but their performance in such tasks has yet to be comprehensively evaluated against humans, and no study has tested Generative Pre‐Trained Transformer (GPT)‐4, the biggest LLM so far. This pre‐registered study uses a “human‐out‐of‐the‐loop” approach to evaluate GPT‐4's capability in title/abstract screening, full‐text review and data extraction across various literature types and languages. Although GPT‐4 had accuracy on par with human performance in some tasks, results were skewed by chance agreement and dataset imbalance. Adjusting for these caused performance scores to drop across all stages: for data extraction, performance was moderate, and for screening, it ranged from none in highly balanced literature datasets (~1:1) to moderate in those datasets where the ratio of inclusion to exclusion in studies was imbalanced (~1:3). When screening full‐text literature using highly reliable prompts, GPT‐4's performance was more robust, reaching “human‐like” levels. Although our findings indicate that, currently, substantial caution should be exercised if LLMs are being used to conduct systematic reviews, they also offer preliminary evidence that, for certain review tasks delivered under specific conditions, LLMs can rival human performance.

Publisher

Wiley

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3