Root Defence Strategies: Ensuring Safety of LLM at the Decoding Level

Documenti analoghi

• MMDT: Decoding the Trustworthiness and Safety of Multimodal Foundation Models
  di: Xu, Chejian, et al.
  Pubblicazione: (2025)
• MLLM-Protector: Ensuring MLLM's Safety without Hurting Performance
  di: Pi, Renjie, et al.
  Pubblicazione: (2024)
• Safety is Not Only About Refusal: Reasoning-Enhanced Fine-tuning for Interpretable LLM Safety
  di: Zhang, Yuyou, et al.
  Pubblicazione: (2025)
• PandaGuard: Systematic Evaluation of LLM Safety against Jailbreaking Attacks
  di: Shen, Guobin, et al.
  Pubblicazione: (2025)
• Challenges in Ensuring AI Safety in DeepSeek-R1 Models: The Shortcomings of Reinforcement Learning Strategies
  di: Parmar, Manojkumar, et al.
  Pubblicazione: (2025)