LF-Steering: Latent Feature Activation Steering for Enhancing Semantic Consistency in Large Language Models

Ähnliche Einträge

• Semantics-Adaptive Activation Intervention for LLMs via Dynamic Steering Vectors
  von: Wang, Weixuan, et al.
  Veröffentlicht: (2024)
• Enhancing Semantic Consistency of Large Language Models through Model Editing: An Interpretability-Oriented Approach
  von: Yang, Jingyuan, et al.
  Veröffentlicht: (2025)
• Gradient Co-occurrence Analysis for Detecting Unsafe Prompts in Large Language Models
  von: Yang, Jingyuan, et al.
  Veröffentlicht: (2025)
• Feature Extraction and Steering for Enhanced Chain-of-Thought Reasoning in Language Models
  von: Li, Zihao, et al.
  Veröffentlicht: (2025)
• Enhancing Cross-task Transfer of Large Language Models via Activation Steering
  von: Tang, Xinyu, et al.
  Veröffentlicht: (2025)