Language Model Steering

Ask about this topic

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

283 papers51 papers in the last four weeks, up 65% on the four weeks before. 0.3% of all new papers.

  1. Cross-Lingual Activation Steering for Multilingual Language Models

    Jan 23, 2026Rhitabrat Pokharel, Ameeta Agrawal, Tanay NagarMultilingual Language ModelsLanguage Model Steering

    Department of Computer Science, Portland State University, USA · Independent Researcher

  2. SteerEval: Inference-time Interventions Strengthen Multilingual Generalization in Neural Summarization Metrics

    Jan 22, 2026Silvia Casola, Ryan Soh-Eun Shim, Felicia Körner +2Summarization EvaluationLanguage Model Steering

    MaiNLP, Center for Information and Language Processing, LMU Munich, Germany · Language Science and Technology, Saarland University, Germany

  3. Steering Language Models Before They Speak: Logit-Level Interventions

    Jan 16, 2026Hyeseon An, Shinwoo Park, Hyundong Jin +1Language Model SteeringControllable Text Generation

    Department of Computer Science, Yonsei University, Seoul, South Korea

  4. Bridging Mechanistic Interpretability and Prompt Engineering with Gradient Ascent for Interpretable Persona Control

    Jan 6, 2026Harshvardhan Saini, Yiming Tang, Dianbo LiuLanguage Model SteeringLLM Interpretability

    Indian Institute of Technology (ISM), Dhanbad · National University of Singapore

  5. Language steering in latent space to mitigate unintended code-switching

    Oct 11, 2025Andrey Goncharov, Nikolai Kondusov, Alexey ZaytsevLanguage Model SteeringMultilingual Language Models

  6. Psychological Steering in LLMs: An Evaluation of Effectiveness and Trustworthiness

    Oct 6, 2025Amin Banayeeanzade, Ala N. Tak, Fatemeh Bahrani +5Language Model SteeringPersonality Modeling in Language Models

    Department of Computer Science, University of Southern California · Institute for Creative Technologies, University of Southern California · Department of Statistics and Data Science, University of California, Los Angeles

  7. Eyes-on-Me: Scalable RAG Poisoning through Transferable Attention-Steering Attractors

    Oct 1, 2025Yen-Shan Chen, Sian-Yao Huang, Cheng-Lin Yang +1Language Model SteeringRAG Poisoning Attacks

    CyCraft AI Lab, Taiwan · National Taiwan University

  8. VISOR++: Universal Visual Inputs based Steering for Large Vision Language Models

    Sep 29, 2025Ravikumar Balakrishnan, Mansi PhuteLanguage Model SteeringLarge Vision-Language Models

    HiddenLayer, USA · Georgia Institute of Technology, USA

  9. EasySteer: A Unified Framework for High-Performance and Extensible LLM Steering

    Sep 29, 2025Haolei Xu, Xinyu Mei, Yuchen Yan +5Language Model SteeringActivation Steering

    1Zhejiang University

  10. Breaking the Mirror: Activation-Based Mitigation of Self-Preference in LLM Evaluators

    Sep 3, 2025Dani Roytburg, Matthew Bozoukov, Matthew Nguyen +3LLM-as-a-JudgeLanguage Model Steering

    School of Computer Science Carnegie Mellon University Pittsburgh, PA 15213 · Martian Research San Francisco, CA, 94105

  11. Adaptive Activation Steering for Efficient LLM Reasoning via Closed-Loop PID Control

    Jun 23, 2025Aryasomayajula Ram BharadwajLanguage Model SteeringEfficient Language Model Inference

    Independent Researcher

  12. REAL: Reading Out Transformer Activations for Precise Localization in Language Model Steering

    Jun 10, 2025Li-Ming Zhan, Bo Liu, Chengqiang Xie +2Transformer InterpretabilityLanguage Model Steering

    Department of Data Science and Artificial Intelligence The Hong Kong Polytechnic University Hong Kong S.A.R.

  13. LiSeCo: Linear Semantic Control for Language Generation

    May 24, 2024Emily Cheng, Carmen Amo AlonsoLanguage Model SteeringControllable Text Generation

    Universitat Pompeu Fabra, Barcelona, Spain · Stanford University, CA, USA