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

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

  2. 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

  3. 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

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

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

  5. 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

  6. A Financial Brain Scan of the LLM

    Aug 29, 2025Hui Chen, Antoine Didisheim, Mo Pourmohammadi +2LLM InterpretabilityLanguage Model Steering

  7. 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

  8. LiSeCo: Linear Semantic Control for Language Generation

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

  9. Coherence boosting: When your pretrained language model is not paying enough attention

    Oct 15, 2021Esmeralda S. Whitammer, Zhen Wang, Nebojsa JojicLong-Context Language Model InferenceLong-Context Language Modeling