Q-resafe: Assessing Safety Risks and Quantization-aware Safety Patching for Quantized Large Language Models

Documenti analoghi

• Token-Level Inference-Time Alignment for Vision-Language Models
  di: Chen, Kejia, et al.
  Pubblicazione: (2025)
• SHAPE : Self-Improved Visual Preference Alignment by Iteratively Generating Holistic Winner
  di: Chen, Kejia, et al.
  Pubblicazione: (2025)
• SecPE: Secure Prompt Ensembling for Private and Robust Large Language Models
  di: Zhang, Jiawen, et al.
  Pubblicazione: (2025)
• Activation Approximations Can Incur Safety Vulnerabilities Even in Aligned LLMs: Comprehensive Analysis and Defense
  di: Zhang, Jiawen, et al.
  Pubblicazione: (2025)
• Confidence-Aware Alignment Makes Reasoning LLMs More Reliable
  di: Chen, Kejia, et al.
  Pubblicazione: (2026)