Open access
Jul 2026
LLM-as-a-judge for infection prevention and control and antimicrobial resistance impact: comparing three main LLMs vs. human experts' assessment
LLMs exhibit a consistent leniency bias, systematically overestimating the quality of AMR-related health communication compared to human evaluators, and are best suited as a scalable screening tool within supervised human-in-the-loop workflows.
M. Di Pumpo, L. Villani, M. R. Gualano et al.
· Frontiers in Public Health · 2 citations