Beware of large language models for scoping literature searches

2025/10/01 by Ryan David Williams, R. W. Butler, Leigh Anne White · 1 voice
Medicine · #Artificial Intelligence in Healthcare and Education

paper · doi:10.1136/rapm-2025-107204

openalex publication_date 2025/10/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/16

Abstract

We read with interest the article by Dr Purwel and colleagues on the potential applications of large language models (LLMs) in meta-analyses and systematic reviews.[1][1] While we agree that LLMs could significantly reduce the time required for the laborious components of systematic reviews, we wish

Discussions

• How much do you trust AI searches We asked the question does perioperative methadone reduce chronic post surgical pain Some convincing lies reported. We fact checked and got it to admit the lies. A [bsky, 1 points, 0 comments]

Related

• Large language models streamline automated systematic review: A preliminary study
• The emergence of large language models as tools in literature reviews: a large language model-assisted systematic review
• Can large language models fully automate or partially assist paper selection in systematic reviews?
• High-performance automated abstract screening with large language model ensembles
• Scientific Knowledge Discovery in the Age of Large Language Models