ClinicalMC benchmark evaluates LLMs on multi-course clinical decisions

Arxiv CS.AI (top papers)

ClinicalMC is a new benchmark designed to assess LLMs on multi-course clinical decision-making tasks. It includes diverse patient cases and evaluates models across multiple treatment stages.

llm

Arxiv CS.AI (top papers)·Ruihui HouSiyi ZhuZiyue HuaiGuangya YuYongqi FanChunming WangTong Ruan

8 days ago