Validating Large Language Models for Title-Abstract Screening in Low-Prevalence Systematic Reviews: An Environmental Science Case Study

Literature screening is a major bottleneck in systematic reviews, yet Large Language Models (LLMs) can substantially reduce workloads. However, performance varies across models and is sensitive to evaluation metrics, particularly in low-prevalence screening contexts. We validated five LLMs (GPT-4.1,...

Celý popis

Podrobná bibliografie

Hlavní autoři:	Maximilian Nawrath, Andrea Merlina, Jemmima Knight, Sam A. Welch, Mahla Rashidian, Isabel Seifert-Dähnn
Médium:	Artigo
Jazyk:	Inglês
Vydáno:	MDPI AG 2026-05-01
Edice:	Information
Témata:	systematic reviews title-abstract screening large language models evidence synthesis inter-rater reliability prevalence paradox
On-line přístup:	https://www.mdpi.com/2078-2489/17/5/501
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!