Lignende værker

• CausalDetox: Causal Head Selection and Intervention for Language Model Detoxification
  af: Wang, Yian, et al.
  Udgivet: (2026)
• Detoxification of Large Language Models through Output-layer Fusion with a Calibration Model
  af: Tian, Yuanhe, et al.
  Udgivet: (2025)
• Fusion Steering: Prompt-Specific Activation Control
  af: Chang, Waldemar, et al.
  Udgivet: (2025)
• Towards Inference-time Category-wise Safety Steering for Large Language Models
  af: Bhattacharjee, Amrita, et al.
  Udgivet: (2024)
• Activation Scaling for Steering and Interpreting Language Models
  af: Stoehr, Niklas, et al.
  Udgivet: (2024)