Towards Evaluating Proactive Risk Awareness of Multimodal Language Models

Documenti analoghi

• GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher
  di: Yuan, Youliang, et al.
  Pubblicazione: (2023)
• LogicAsker: Evaluating and Improving the Logical Reasoning Ability of Large Language Models
  di: Wan, Yuxuan, et al.
  Pubblicazione: (2024)
• Refuse Whenever You Feel Unsafe: Improving Safety in LLMs via Decoupled Refusal Training
  di: Yuan, Youliang, et al.
  Pubblicazione: (2024)
• Can't See the Forest for the Trees: Benchmarking Multimodal Safety Awareness for Multimodal LLMs
  di: Wang, Wenxuan, et al.
  Pubblicazione: (2025)
• Insight Over Sight: Exploring the Vision-Knowledge Conflicts in Multimodal LLMs
  di: Liu, Xiaoyuan, et al.
  Pubblicazione: (2024)