Using GPT‐4 for Title and Abstract Screening in a Literature Review of Public Policies: A Feasibility Study

ABSTRACT Introduction We describe the first known use of large language models (LLMs) to screen titles and abstracts in a review of public policy literature. Our objective was to assess the percentage of articles GPT‐4 recommended for exclusion that should have been included (“false exclusion rate”)...

ver descrição completa

Detalhes bibliográficos

Principais autores:	Max Rubinstein, Sean Grant, Beth Ann Griffin, Seema Choksy Pessar, Bradley D. Stein
Formato:	Artigo
Idioma:	Inglês
Publicado em:	Wiley 2025-05-01
Colecção:	Cochrane Evidence Synthesis and Methods
Assuntos:	evidence synthesis GPT‐4 large language model opioids policy
Acesso em linha:	https://doi.org/10.1002/cesm.70031
Tags:	Adicionar Tag Sem tags, seja o primeiro a adicionar uma tag!