Overview

Language model steering studies how to make a pretrained model change a particular behavior—such as tone, refusal, truthfulness, reasoning, or language—without necessarily retraining its weights. Common approaches add contrastive activation vectors, target sparse features or specific neurons and attention heads, or adapt interventions to the prompt and the model’s evolving state; other methods guide logits, decoding, or agent-level decisions. Researchers evaluate these methods on tasks ranging from safety and factuality to personalization, multilingual generation, and reasoning, measuring both target behavior and preservation of general capabilities. A central open challenge is reliable, selective control: a behavior may be readable in activations yet resist intervention, while steering can cause collateral quality loss, prompt sensitivity, or safety trade-offs.

Latest papers

CardsList

311 papers28 papers in the last four weeks, down 48% on the four weeks before. 0.2% of all new papers.

  1. What MoE Routing Controls: Causal Interventions on Expert Trajectories

    Nov 17, 2026Mukund Athmaram, Manoj Rao, Liang MaMixture-of-Experts Language ModelsLanguage Model Steering

  2. Do Probing and Steering Favor the Same Directions Within and Across Language Models?

    Nov 14, 2026Afshin Sadeghi, Daniel BeckerLanguage Model SteeringActivation Steering

  3. Mean-field Token Steering

    Nov 14, 2026Md Zulfiqur Haider, Asmaa Eldesoukey, Abhishek Halder +1Language Model SteeringSchrödinger Bridges

  4. Right Token, Right Time: From Per-Token Gating to Trajectory-Aware Activation Steering

    Nov 13, 2026Nima Eshraghi, Lovedeep Gondara, Sagarika Suresh +3Language Model SteeringActivation Steering

  5. Activation Steering the Nan-Shan in Typhoon

    Nov 13, 2026Megan Wei, Damon Pham, John Cayley +1Controllable Text GenerationLanguage Model Steering

  6. Safety Side Effects of Preventative Persona Steering: An Empirical Audit

    Nov 13, 2026Sabrina Tang, Nikolai Vo, Carson Murillo +2Language Model SteeringActivation Steering

  7. FPSRG: Heterogeneous User Simulation First-Person Post-Training and Multidimensional Semantic Response Grids

    Nov 12, 2026Ruimin Pei, Haibo Liu, Fang Zhang +1User SimulationLarge Language Model-Based Social Simulation

  8. Policy Over Purpose: Auditing LLM Content Moderation of Reclaimed Slur Usage

    Nov 6, 2026Christina Chance, Kai-Wei ChangContent ModerationLLM Auditing

  9. Mind Control of LLMs via Closed-Loop Stimulation: Out-of-Distribution Robustness

    Nov 4, 2026Kasra Fallah, Rudramani Singha, Hannah Ghanei +3Language Model SteeringLanguage Model Robustness

  10. When Should an LLM Steering Edit Depend on the Input?

    Nov 3, 2026Rachael Harkness, Konrad RawlikLanguage Model SteeringActivation Steering

  11. AdSteer: Native Advertising in Large Language Model Generation

    Nov 3, 2026Shuhang Lin, Chuhao Zhou, Zhenyu Wang +4Online AdvertisingLanguage Model Steering

  12. VIAS: Value-Isolating Activation Steering for Multi-Value Alignment and Compliance for Organisations

    Nov 2, 2026Avni Mittal, Avinash Anand, Dikshant Kukreja +3LLM AlignmentLanguage Model Steering

  13. Steering with Multilingual Lexicons for Sentiment Control in Low-Resource Languages

    Nov 2, 2026Lucinda Laurent, Muhammad Dehan Al Kautsar, Alfan Farizki Wicaksono +1Language Model SteeringActivation Steering

  14. UPSHIFT: User Preference Steering from Human-AI Interaction Feedback Traces

    Nov 2, 2026Jingping Wang, Zhanhao Li, Shao Zhang +1Personalized Language ModelsLanguage Model Steering

  15. Sweep Less, Steer More: Using Activation Steering Geometry for Reduced Hyperparameter Search

    Nov 1, 2026Nishkal Hundia, Swastik Agrawal, Navita Goyal +1Language Model SteeringActivation Steering

  16. TopoSteer: Topological Layer Selection for Activation Steering in LLMs

    Nov 1, 2026Tuc Nguyen, Marcos Gutiérrez-del-Pozo, Eduardo Paluzo-Hidalgo +3Language Model SteeringActivation Steering

  17. Steering Readerly Dynamics: Trajectory-Guided Story Generation with Large Language Models

    Oct 30, 2026Danrui Li, Yiwei Zhao, Mubbasir Kapadia +1Narrative GenerationLanguage Model Steering

  18. Orthogonal and Parametrized Multi-Attribute Steering of LLMs

    Oct 27, 2026Remy Ogasawara, Cullen Anderson, Narmeen Fatimah Oozeer +4Language Model SteeringActivation Steering

  19. CANS: Capability-Preserving Neuron Steering for Large Language Models

    Oct 26, 2026Yucheng Wu, Chengyi Xie, Chenpeng Wang +1Language Model SteeringSafety-Utility Trade-Off in Language Models

  20. Neyman Orthogonal Activation Steering

    Oct 23, 2026David Arbour, Erfan Jahanparast, Serina Chang +1Language Model SteeringActivation Steering

  21. DIAL: Steerable Language Models with Distilled Instruction-Adherence Levels

    Oct 22, 2026Thanh Q. Tran, John Russell Himawan, Arun Verma +4Language Model SteeringInstruction Following

  22. RealControlBench: A Benchmark for Interpretability-Informed Fine-Grained Control of LLMs and Agents

    Oct 19, 2026Xinying Cai, Bin Hu, Mingyu Jin +16Language Model SteeringLanguage Model-Based Control

  23. From Black Box to Controller: Inference-Time Steering of LLM via Feature Amplification

    Oct 19, 2026Keqi Chen, Zekai Sun, Yuhua Wen +5Language Model SteeringControllable Text Generation

  24. Compositional Activation Steering Across Languages and Behaviors with Contextual Gates

    Oct 17, 2026Daniil Gurgurov, Akansh Maurya, Josef van Genabith +2Language Model SteeringActivation Steering