Koyar Afrasyab

1. Judge-dependent safety gains and model-specific helpfulness costs of evidence-sufficiency prompting in clinical LLMs
   2026/07/20 by Koyar Afrasyab
   #cs.AI
2. Evaluating medical AI under missing information: same-provider judges and human raters change apparent safety
   2026/07/21 by Koyar Afrasyab
   #cs.AI