Same Verdict, Different Reasons: LLM-as-a-Judge and Clinician Disagreement on Medical Chatbot Completeness

Documenti analoghi

• MedScore: Generalizable Factuality Evaluation of Free-Form Medical Answers by Domain-adapted Claim Decomposition and Verification
  di: Huang, Heyuan, et al.
  Pubblicazione: (2025)
• Can one size fit all?: Measuring Failure in Multi-Document Summarization Domain Transfer
  di: DeLucia, Alexandra, et al.
  Pubblicazione: (2025)
• Evaluating Implicit Biases in LLM Reasoning through Logic Grid Puzzles
  di: Jahara, Fatima, et al.
  Pubblicazione: (2025)
• Transferring Fairness using Multi-Task Learning with Limited Demographic Information
  di: Aguirre, Carlos, et al.
  Pubblicazione: (2023)
• Predicting Disagreement with Human Raters in LLM-as-a-Judge Difficulty Assessment without Using Generation-Time Probability Signals
  di: Ehara, Yo
  Pubblicazione: (2026)