AdvChain: Adversarial Chain-of-Thought Tuning for Robust Safety Alignment of Large Reasoning Models

Documenti analoghi

• To Think or Not to Think: Exploring the Unthinking Vulnerability in Large Reasoning Models
  di: Zhu, Zihao, et al.
  Pubblicazione: (2025)
• SafeChain: Safety of Language Models with Long Chain-of-Thought Reasoning Capabilities
  di: Jiang, Fengqing, et al.
  Pubblicazione: (2025)
• LaRS: Latent Reasoning Skills for Chain-of-Thought Reasoning
  di: Xu, Zifan, et al.
  Pubblicazione: (2023)
• CARFT: Boosting LLM Reasoning via Contrastive Learning with Annotated Chain-of-Thought-based Reinforced Fine-Tuning
  di: Zhu, Wenqiao, et al.
  Pubblicazione: (2025)
• Mitigating Misleading Chain-of-Thought Reasoning with Selective Filtering
  di: Wu, Yexin, et al.
  Pubblicazione: (2024)