AlphaSteer: Learning Refusal Steering with Principled Null-Space Constraint

Documenti analoghi

• AdaSteer: Your Aligned LLM is Inherently an Adaptive Jailbreak Defender
  di: Zhao, Weixiang, et al.
  Pubblicazione: (2025)
• Compiling Activation Steering into Weights via Null-Space Constraints for Stealthy Backdoors
  di: Yin, Rui, et al.
  Pubblicazione: (2026)
• AlphaAlign: Incentivizing Safety Alignment with Extremely Simplified Reinforcement Learning
  di: Zhang, Yi, et al.
  Pubblicazione: (2025)
• SARSteer: Safeguarding Large Audio-Language Models via Safe-Ablated Refusal Steering
  di: Lin, Weilin, et al.
  Pubblicazione: (2025)
• MASKDROID: Robust Android Malware Detection with Masked Graph Representations
  di: Zheng, Jingnan, et al.
  Pubblicazione: (2024)