Why Steering Works: Toward a Unified View of Language Model Parameter Dynamics

arXiv:2602.02343v3 Announce Type: replace-cross Abstract: Methods for controlling large language models (LLMs), including local weight fine-tuning, LoRA-based adaptation, and activation-based interventions, are often studied in isolation, obscuring their connections and making comparison difficult. In this work, we present a unified view that frames these interventions as dynamic weight updates induced by a control signal, placing them within a single conceptual framework. Building on this view,