This paper is in the following e-collection/theme issue:

New Methods (941) Generative Language Models Including ChatGPT (299) Artificial Intelligence (1351) Chatbots and Conversational Agents (527)

Published on in Vol 26 (2024)

Preprints (earlier versions) of this paper are available at https://preprints.jmir.org/preprint/52758, first published .
Human-Comparable Sensitivity of Large Language Models in Identifying Eligible Studies Through Title and Abstract Screening: 3-Layer Strategy Using GPT-3.5 and GPT-4 for Systematic Reviews

Human-Comparable Sensitivity of Large Language Models in Identifying Eligible Studies Through Title and Abstract Screening: 3-Layer Strategy Using GPT-3.5 and GPT-4 for Systematic Reviews

Human-Comparable Sensitivity of Large Language Models in Identifying Eligible Studies Through Title and Abstract Screening: 3-Layer Strategy Using GPT-3.5 and GPT-4 for Systematic Reviews

Authors of this article:

Kentaro Matsui1, 2 Author Orcid Image ;   Tomohiro Utsumi2, 3 Author Orcid Image ;   Yumi Aoki4 Author Orcid Image ;   Taku Maruki5 Author Orcid Image ;   Masahiro Takeshima6 Author Orcid Image ;   Yoshikazu Takaesu7 Author Orcid Image
Article Authors Cited by Tweetations (41) Metrics

There are no citations yet available for this article according to Crossref .