cs.CLFeb 2, 2026

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

Authors: Ziwen Xu, Chenyan Wu, Hengyu Sun, Haiwen Hong, Mengru Wang, Yunzhi Yao, Longtao Huang, Hui Xue, 

Organizations: Zhejiang University · Alibaba Group

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, we propose a unified preference-utility analysis that separates control effects into preference, defined as the tendency toward a target concept, and utility, defined as coherent and task-valid generation, and measures both on a shared log-odds scale using polarity-paired contrastive examples. Across methods, we observe a consistent trade-off between preference and utility: stronger control increases preference while predictably reducing utility. We further explain this behavior through an activation manifold perspective, in which control shifts representations along target-concept directions to enhance preference, while utility declines primarily when interventions push representations off the model's valid-generation manifold. Finally, we introduce a new steering approach SPLIT guided by this analysis that improves preference while better preserving utility. Code is available at https://github.com/zjunlp/EasyEdit/blob/main/examples/SPLIT.md.

Figures & tables

Appendix figures & tables6 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Towards Understanding Steering Strength

    Feb 2, 2026Magamed Taimeskhanov, Samuel Vaiter, Damien GarreauLanguage Model SteeringActivation Steering

  2. Steer Like the LLM: Activation Steering that Mimics Prompting

    May 5, 2026Geert Heyman, Frederik VandeputteLanguage Model SteeringLLM Prompting

  3. One Model for All: Multi-Objective Controllable Language Models

    Apr 6, 2026Qiang He, Yucheng Yang, Tianyi Zhou +3Multi-Objective Language Model AlignmentControllable Text Generation