记/基准] RELIABLE AND DIVERSE EVALUATION OF LLM MEDICAL KNOWLEDGE MASTERY
记/基准:RELIABLE AND DIVERSE EVALUATION OF LLM MEDICAL KNOWLEDGE MASTERY
引言:当AI医生遇上“考试”想象一下,你生病了,去问一个AI医生:“我头痛发烧,应该吃什么药?”如果它回答“吃冰淇淋…
2026/7/25 18:17:22