Tag
This study evaluates AI-generated summaries for cancer patients using a dual assessment framework with human domain experts and LLMs as evaluators, focusing on accuracy, clinical relevance, and safety in healthcare applications.
This paper evaluates whether clinician pairwise preferences reliably indicate clinical safety in LLMs, using 26,804 judgments from 736+ clinicians across 13 models. It finds that preference rankings poorly track safety-critical failures and proposes a clinically adjusted ranking that better incorporates rubric-based safety signals.
This paper proposes a multi-agent 'Trust but Verify' system to reduce medical hallucinations in LLMs. It tests three open-access models on clinical questions about banned drugs and achieves a 53% reduction in hallucination error rate.