Selective Steering: Norm-Preserving Control Through Discriminative Layer Selection

Documenti analoghi

• MoD: A Distribution-Based Approach for Merging Large Language Models
  di: Dang, Quy-Anh, et al.
  Pubblicazione: (2024)
• Reinforcement Learning for Reasoning in Small LLMs: What Works and What Doesn't
  di: Dang, Quy-Anh, et al.
  Pubblicazione: (2025)
• Adaptive Acquisition Selection for Bayesian Optimization with Large Language Models
  di: Ngo, Giang, et al.
  Pubblicazione: (2026)
• Global Evolutionary Steering: Refining Activation Steering Control via Cross-Layer Consistency
  di: Jiang, Xinyan, et al.
  Pubblicazione: (2026)
• Diversity Progress for Goal Selection in Discriminability-Motivated RL
  di: Lintunen, Erik M., et al.
  Pubblicazione: (2024)