SafeDialBench: A Fine-Grained Safety Evaluation Benchmark for Large Language Models in Multi-Turn Dialogues with Diverse Jailbreak Attacks

Documenti analoghi

• Efficient Reinforcement Learning with Semantic and Token Entropy for LLM Reasoning
  di: Cao, Hongye, et al.
  Pubblicazione: (2025)
• Thinking-Based Non-Thinking: Solving the Reward Hacking Problem in Training Hybrid Reasoning Models via Reinforcement Learning
  di: Gan, Siyuan, et al.
  Pubblicazione: (2026)
• Causal Information Prioritization for Efficient Reinforcement Learning
  di: Cao, Hongye, et al.
  Pubblicazione: (2025)
• Model-Based Offline Reinforcement Learning with Adversarial Data Augmentation
  di: Cao, Hongye, et al.
  Pubblicazione: (2025)
• Towards Empowerment Gain through Causal Structure Learning in Model-Based RL
  di: Cao, Hongye, et al.
  Pubblicazione: (2025)