Answers are grounded in this paper and cite their sources.
Observational analysis uncovers accuracy issues in literature reviews using large language models, suggesting potential enhancements.
Large language models (LLMs) failed to fully replicate peer-reviewed methodologies, producing outputs with inaccuracies but identifying relevant, especially recent, articles missed by the references. While human-led PRISMA-based reviews remain the gold standard, refining LLMs for literature reviews shows potential.
No takes yet. Share an insight, caveat, or question.
Bakare et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: