A Coin Flip for Safety: LLM Judges Fail to Reliably Measure Adversarial Robustness

Documenti analoghi

• A Generative Approach to LLM Harmfulness Mitigation with Red Flag Tokens
  di: Dobre, David, et al.
  Pubblicazione: (2025)
• LLM-Safety Evaluations Lack Robustness
  di: Beyer, Tim, et al.
  Pubblicazione: (2025)
• AdversariaLLM: A Unified and Modular Toolbox for LLM Robustness Research
  di: Beyer, Tim, et al.
  Pubblicazione: (2025)
• Fast Proxies for LLM Robustness Evaluation
  di: Beyer, Tim, et al.
  Pubblicazione: (2025)
• Extracting Unlearned Information from LLMs with Activation Steering
  di: Seyitoğlu, Atakan, et al.
  Pubblicazione: (2024)