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. Dual-Stance Evaluation of Sycophancy: The Structure of Agreement and the Limits of Intervention

    Apr 22, 2026Matthew James BuchanLLM SycophancyLanguage Model Steering

    Independent Researcher, United Kingdom.

  2. Semantic Prompting: Agentic Incremental Narrative Refinement through Spatial Semantic Interaction

    Apr 21, 2026Xuxin Tang, Ibrahim Tahmid, Eric Krokos +3Grounded Text GenerationLanguage Model Steering

    Virginia Tech Blacksburg, VA, United States · Department of Defense United States

  3. The Geometric Canary: Predicting Steerability and Detecting Drift via Representational Stability

    Apr 20, 2026Prashant C. RajuLanguage Model SteeringLLM Reliability

  4. Are Emotion and Rhetoric Neurons in LLM? Neuron Recognition and Adaptive Masking for Emotion-Rhetoric Prediction Steering

    Apr 19, 2026Li Zheng, Xin Zhang, Shuyi He +5Language Model SteeringLLM Interpretability

    Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, School of Cyber Science and Engineering, Wuhan University, Wuhan, China · Ant International · School of Computing Technologies, RMIT University, Australia

  5. MidSteer: Optimal Affine Framework for Steering Generative Models

    Apr 17, 2026Tatiana Gaintseva, Andrew Stepanov, Ziquan Liu +4Language Model SteeringGenerative Modeling

    Queen Mary University of London, London, UK · Huawei Noah’s Ark, London, UK · QuantumLight Capital, London, UK +2

  6. Predicting Where Steering Vectors Succeed

    Apr 16, 2026Jayadev BillaLanguage Model SteeringRepresentation Steering

  7. FineSteer: A Unified Framework for Fine-Grained Inference-Time Steering in Large Language Models

    Apr 16, 2026Zixuan Weng, Jinghuai Zhang, Kunlin Cai +3Language Model SteeringLLM Safety

    University of California, Los Angeles

  8. Psychological Steering of Large Language Models

    Apr 15, 2026Leonardo Blas, Robin Jia, Emilio FerraraLanguage Model SteeringRepresentation Engineering

    Thomas Lord Department of Computer Science, University of Southern California, Los Angeles, CA 90089

  9. From Weights to Activations: Is Steering the Next Frontier of Adaptation?

    Apr 15, 2026Simon Ostermann, Daniil Gurgurov, Tanja Baeumel +4Online Language Model AdaptationLanguage Model Steering

    Saarland University · German Research Center for Artificial Intelligence (DFKI) · Centre for European Research in Trusted AI (CERTAIN) +6

  10. Beyond Static Personas: Situational Personality Steering for Large Language Models

    Apr 15, 2026Zesheng Wei, Mengxiang Li, Zilei Wang +1Language Model SteeringPersonality Modeling in Language Models

    University of Science and Technology of China · Singapore Management University

  11. Beyond Prompt: Fine-grained Simulation of Cognitively Impaired Standardized Patients via Stochastic Steering

    Apr 14, 2026Weikang Zhang, Zimo Zhu, Zhichuan Yang +3Large Language Model-Based Role-Play SimulationLanguage Model Steering

    School of Software, Xi’an Jiaotong University · Institute of Data Science, National University of Singapore · College of Computer Science, Sichuan University +1

  12. DeCoVec: Building Decoding Space based Task Vector for Large Language Models via In-Context Learning

    Apr 13, 2026Feiyang Li, Yile WangLanguage Model SteeringTask Vectors

    College of Computer Science and Software Engineering, Shenzhen University

  13. A Systematic Analysis of the Impact of Persona Steering on LLM Capabilities

    Apr 13, 2026Jiaqi Chen, Ming Wang, Tingna Xie +2Language Model SteeringPersonality Modeling in Language Models

    School of Computer Science and Engineering, Northeastern University, Shenyang 110819, China · School of Computing and Information Systems, Singapore Management University, Singapore 178902, Singapore · School of Computer and Communication Engineering, Northeastern University, Qinhuangdao 066004, China

  14. From Words to Widgets for Controllable LLM Generation

    Apr 13, 2026Chao Zhang, Yiren Liu, Lunyiu Nie +3LLM PromptingControllable Text Generation

    Cornell University Ithaca, NY, USA · University of Illinois Urbana-Champaign Champaign, IL, USA · The University of Texas at Austin Austin, TX, USA +1

  15. ExecTune: Effective Steering of Black-Box LLMs with Guide Models

    Apr 9, 2026Vijay Lingam, Aditya Golatkar, Anwesan Pal +6Language Model SteeringLLM Inference Efficiency

    AWS AI

  16. What Drives Representation Steering? A Mechanistic Case Study on Steering Refusal

    Apr 9, 2026Stephen Cheng, Sarah Wiegreffe, Dinesh ManochaLanguage Model SteeringLLM Interpretability

    University of Maryland, College Park

  17. Persona Matters: Effects of Activation Steering on Short Answer Generation and Scoring

    Apr 8, 2026Yongchao Wu, Aron HenrikssonOpen-Ended GenerationLanguage Model Steering

    Stockholm University, NOD-huset, Borgarfjordsgatan 12, 16455 Stockholm, Sweden

  18. LLM Reasoning as Trajectories: Step-Specific Representation Geometry and Correctness Signals

    Apr 7, 2026Lihao Sun, Hang Dong, Bo Qiao +3LLM ReasoningRepresentation Geometry in Language Models

    Microsoft

  19. Extracting and Steering Emotion Representations in Small Language Models: A Methodological Comparison

    Apr 5, 2026Jihoon JeongEmotion Representation in Language ModelsSmall Language Models

    Department of Electrical Engineering and Computer Science Daegu Gyeongbuk Institute of Science and Technology (DGIST) ModuLabs

  20. Where to Steer: Input-Dependent Layer Selection for Steering Improves LLM Alignment

    Apr 4, 2026Soham Gadgil, Chris Lin, Su-In LeeLanguage Model SteeringInference-Time Language Model Alignment

    University of Washington

  21. LangFIR: Discovering Sparse Language-Specific Features from Monolingual Data for Language Steering

    Apr 4, 2026Sing Hieng Wong, Hassan Sajjad, A. B. SiddiqueLanguage Model SteeringMultilingual Language Models

    Department of Computer Science, University of Kentucky, USA · Department of Computer Science, Dalhousie University, Canada

  22. Noise Steering for Controlled Text Generation: Improving Diversity and Reading-Level Fidelity in Arabic Educational Story Generation

    Apr 3, 2026Haziq Mohammad Khalid, Salsabeel Shapsough, Imran ZualkernanText GenerationDiverse Text Generation

    American University of Sharjah

  23. Valence-Arousal Subspace in LLMs: Circular Emotion Geometry and Multi-Behavioral Control

    Apr 3, 2026Lihao Sun, Lewen Yan, Xiaoya Lu +3Emotion Representation in Language ModelsLanguage Model Steering

    University of Chicago · Shanghai AI Lab · Harvard University

  24. Steerable but Not Decodable: Function Vectors Operate Beyond the Logit Lens

    Apr 3, 2026Mohammed Suhail B NadafFunction VectorsTransformer Interpretability

    Independent

  25. Reliable Control-Point Selection for Steering Reasoning in Large Language Models

    Apr 2, 2026Haomin Zhuang, Hojun Yoo, Xiaonan Luo +2Language Model SteeringActivation Steering

    University of Notre Dame

  26. Agenda-based Narrative Extraction: Steering Pathfinding Algorithms with Large Language Models

    Mar 31, 2026Brian Felipe Keith-Norambuena, Carolina Inés Rojas-Córdova, Claudio Juvenal Meneses-Villegas +4Language Model SteeringInteractive Storytelling

    Department of Computing and Systems Engineering, Universidad Católica del Norte, Antofagasta, Chile · Department of Industrial Engineering, Universidad Católica del Norte, Antofagasta, Chile · Department of Chemical and Environmental Engineering, Universidad Católica del Norte, Antofagasta, Chile

  27. Steering Code LLMs with Activation Directions for Language and Library Control

    Mar 24, 2026Md Mahbubur Rahman, Arjun Guha, Harshitha MenonLanguage Model SteeringCode Language Models

    Iowa State University · Northeastern University · Lawrence Livermore National Laboratory

  28. Steering LLMs for Culturally Localized Generation

    Mar 24, 2026Simran Khanuja, Hongbin Liu, Shujian Zhang +4Cultural Knowledge in Language ModelsCultural Bias in Language Models

    Carnegie Mellon University · Google DeepMind

  29. LLM-guided headline rewriting for clickability enhancement without clickbait

    Mar 23, 2026Yehudit Aperstein, Linoy Halifa, Sagiv Bar +1Text GenerationControllable Text Generation

    Intelligent Systems, Afeka Academic College of Engineering, Tel Aviv 69988, Israel · School of Computer Science, Faculty of Sciences, HIT-Holon Institute of Technology, Holon 58102, Israel

  30. Persona Vectors in Games: Measuring and Steering Strategies via Activation Vectors

    Mar 22, 2026Johnathan Sun, Andrew ZhangPersonality Modeling in Language ModelsLanguage Model Steering

    Harvard University