Reasoning as an Adaptive Defense for Safety

Documenti analoghi

• Testing the Limits of Jailbreaking Defenses with the Purple Problem
  di: Kim, Taeyoun, et al.
  Pubblicazione: (2024)
• Conservative Prediction via Data-Driven Confidence Minimization
  di: Choi, Caroline, et al.
  Pubblicazione: (2023)
• Weight Ensembling Improves Reasoning in Language Models
  di: Dang, Xingyu, et al.
  Pubblicazione: (2025)
• Mitigating Bias in RAG: Controlling the Embedder
  di: Kim, Taeyoun, et al.
  Pubblicazione: (2025)
• Heuristic Algorithm-based Action Masking Reinforcement Learning (HAAM-RL) with Ensemble Inference Method
  di: Choi, Kyuwon, et al.
  Pubblicazione: (2024)