Overview

Activation steering studies how edits to a model’s hidden activations can control its behavior at inference time, enabling changes without retraining the full model. Common approaches add or remove contrastive steering vectors, target sparse autoencoder features, neurons or attention heads, and use conditional or feedback-based controllers to adapt interventions to the input or generation state. Researchers apply these methods to language tasks such as reasoning, refusal, factuality and hallucination mitigation, as well as image and video generation, speech, and embodied agents; evaluations include benchmarks such as GSM8K, TruthfulQA, POPE and LIBERO. A central challenge is that readable or decodable features are not necessarily controllable, and effective edits can vary by context and architecture or cause collateral changes to fluency, utility and safety.

Latest papers

CardsList

417 papers59 papers in the last four weeks, down 9% on the four weeks before. 0.4% of all new papers.

  1. ODESteer: A Unified ODE-Based Steering Framework for LLM Alignment

    Feb 19, 2026Hongjue Zhao, Haosen Sun, Jiangtao Kong +8Language Model SteeringActivation Steering

  2. Discovering Universal Activation Directions for PII Leakage in Language Models

    Feb 19, 2026Leo Marchyok, Zachary Coalson, Sungho Keum +2Privacy Leakage in Language ModelsLLM Interpretability

  3. PERSONA: Dynamic and Compositional Inference-Time Personality Control via Activation Vector Algebra

    Feb 17, 2026Xiachong Feng, Liang Zhao, Weihong Zhong +5Controllable Text GenerationPersonality Modeling in Language Models

  4. Watch the Model Think: On-Policy Extraction of Activation Steering Vectors

    Feb 15, 2026Xuanbo Su, Yingfang Zhang, Hao Luo +3Language Model SteeringRepresentation Steering

  5. Sparse Autoencoders are Capable LLM Jailbreak Mitigators

    Feb 12, 2026Yannick Assogba, Jacopo Cortellazzi, Javier Abad +3Sparse AutoencodersLLM Jailbreak Attacks

  6. TADA! Tuning Audio Diffusion Models through Activation Steering

    Feb 12, 2026Łukasz Staniszewski, Katarzyna Zaleska, Mateusz Modrzejewski +1Controllable Music GenerationAudio Diffusion Models

  7. General and Efficient Steering of Diffusion Models

    Feb 11, 2026Qingsong Wang, Mikhail Belkin, Yusu WangDiffusion Model GuidanceActivation Steering

  8. Mitigating Memorization Where It Happens

    Feb 9, 2026Xuanqi Zhang, Haoyang Shang, Xiaoxiao LiMemorization in Language ModelsPrivacy Leakage in Language Models

  9. Endogenous Resistance to Activation Steering in Language Models

    Feb 6, 2026Alex McKenzie, Keenan Pepper, Stijn Servaes +6Language Model SteeringLanguage Model Robustness

  10. Towards Understanding Steering Strength

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

  11. There Is More to Refusal in Large Language Models than a Single Direction

    Feb 2, 2026Faaiz Joad, Majd Hawasly, Sabri Boughorbel +2LLM InterpretabilityLLM Refusal Behavior

  12. RAPTOR: Ridge-Adaptive Logistic Probes

    Jan 29, 2026Ziqi Gao, Yaotian Zhu, Qingcheng Zeng +4Language Model ProbingActivation Steering

  13. Knowing Bias, Doing Better: Mitigating Social Bias in LLMs via Know-Bias Neuron Enhancement

    Jan 29, 2026Jinhao Pan, Chahat Raj, Anjishnu Mukherjee +4Debiased MLSocial Bias in Language Models

  14. ILRR: Inference-Time Steering Method for Masked Diffusion Language Models

    Jan 29, 2026Eden Avrahami, Eliya NachmaniMasked Diffusion ModelsLanguage Model Steering

  15. VISPA: Pluralistic Alignment via Automatic Value Selection and Activation

    Jan 19, 2026Shenyan Zheng, Jiayou Zhong, Anudeex Shetty +3LLM AlignmentMulti-Objective Language Model Alignment

  16. The Straight and Narrow: Do LLMs Possess an Internal Moral Path?

    Jan 15, 2026Luoming Hu, Jingjie Zeng, Liang Yang +1Moral Reasoning in Language ModelsInference-Time Language Model Alignment

  17. D-STEER: Two-Way Control of DPO-Induced Safety Behavior in Activation Space

    Dec 3, 2025Samarth Raina, Saksham Aggarwal, Amit Dhanda +3Causal Interventions in Language ModelsActivation Steering

  18. Physics Steering: Causal Control of Cross-Domain Concepts in a Physics Foundation Model

    Nov 25, 2025Rio Alexa Fear, Payel Mukhopadhyay, Michael McCabe +2Physical Foundation ModelsActivation Steering

  19. Silence is Golden: Mitigating Hallucinations in Large Audio-Language Models via Layer-Weighted Vector Steering

    Oct 14, 2025Tsung-En Lin, Kuan-Yi Lee, Hung-Yi LeeAudio QAHallucination in Language Models

  20. Turning the Spell Around: Lightweight Alignment Amplification via Rank-One Safety Injection

    Aug 28, 2025Harethah Abu Shairah, Hasan Abed Al Kader Hammoud, George Turkiyyah +1LLM GuardrailsLLM Safety Alignment

  21. LiSeCo: Linear Semantic Control for Language Generation

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