CARES: Comprehensive Evaluation of Safety and Adversarial Robustness in Medical LLMs

Documenti analoghi

• ENCORE: Entropy-guided Reward Composition for Multi-head Safety Reward Models
  di: Li, Xiaomin, et al.
  Pubblicazione: (2025)
• CARES: A Comprehensive Benchmark of Trustworthiness in Medical Vision Language Models
  di: Xia, Peng, et al.
  Pubblicazione: (2024)
• CSSBench: Evaluating the Safety of Lightweight LLMs against Chinese-Specific Adversarial Patterns
  di: Zhou, Zhenhong, et al.
  Pubblicazione: (2026)
• Safer or Luckier? LLMs as Safety Evaluators Are Not Robust to Artifacts
  di: Chen, Hongyu, et al.
  Pubblicazione: (2025)
• The Scales of Justitia: A Comprehensive Survey on Safety Evaluation of LLMs
  di: Liu, Songyang, et al.
  Pubblicazione: (2025)