English
Related papers

Related papers: Programming Refusal with Conditional Activation St…

200 papers

Language models (LMs) are typically post-trained for desired capabilities and behaviors via weight-based or prompt-based steering, but the former is time-consuming and expensive, and the latter is not precisely controllable and often…

Computation and Language · Computer Science 2026-05-18 Sasha Cui , Zhongren Chen

Controlling the behaviors of large language models (LLM) is fundamental to their safety alignment and reliable deployment. However, existing steering methods are primarily driven by empirical insights and lack theoretical performance…

Machine Learning · Computer Science 2026-05-19 Dung V. Nguyen , Hieu M. Vu , Nhi Y. Pham , Lei Zhang , Tan M. Nguyen

Jailbreak prompts can trigger harmful completions on aligned LLMs, In accordance, safety steering has been proposed: test-time activation interventions that steer jailbreak activations to trigger refusal while preserving benign utility.…

Cryptography and Security · Computer Science 2026-05-26 Luoyu Chen , Weiqi Wang , Zhiyi Tian , Chenhan Zhang , Feng Wu , Jianhuan Huang , Ahmed Asiri , Shui Yu

While modern LLMs are aligned to refuse harmful requests, it is essential to understand the underlying mechanistic basis of this refusal behavior for model safety analysis. For example, steering-based jailbreak attacks exploit this by…

Artificial Intelligence · Computer Science 2026-05-28 Su-Hyeon Kim , Hyundong Jin , Yejin Lee , Yo-Sub Han

Safety alignment of large language models currently faces a central challenge: existing alignment techniques often prioritize mitigating responses to harmful prompts at the expense of overcautious behavior, leading models to incorrectly…

Large language models exhibit strong multilingual capabilities, yet significant performance gaps persist between dominant and non-dominant languages. Prior work attributes this gap to imbalances between shared and language-specific neurons…

Computation and Language · Computer Science 2026-01-26 Rhitabrat Pokharel , Ameeta Agrawal , Tanay Nagar

Large Vision-Language Models (LVLMs) exhibit outstanding performance on vision-language tasks but struggle with hallucination problems. Through in-depth analysis of LVLM activation patterns, we reveal two key findings: 1) truthfulness and…

Computer Vision and Pattern Recognition · Computer Science 2026-02-26 Jianghao Yin , Qin Chen , Kedi Chen , Jie Zhou , Xingjiao Wu , Liang He

Large language models can be steered at inference time through prompting or activation interventions, but activation steering methods often underperform compared to prompt-based approaches. We propose a framework that formulates prompt…

Computation and Language · Computer Science 2026-05-06 Geert Heyman , Frederik Vandeputte

Reflection, the ability of large language models (LLMs) to evaluate and revise their own reasoning, has been widely used to improve performance on complex reasoning tasks. Yet, most prior works emphasizes designing reflective prompting…

Machine Learning · Computer Science 2025-12-12 Fu-Chieh Chang , Yu-Ting Lee , Pei-Yuan Wu

Changing the behavior of large language models (LLMs) can be as straightforward as editing the Transformer's residual streams using appropriately constructed "steering vectors." These modifications to internal neural activations, a form of…

Computation and Language · Computer Science 2025-05-20 Jian-Qiao Zhu , Haijiang Yan , Thomas L. Griffiths

The increasing capabilities of large generative models and their ever more widespread deployment have raised concerns about their reliability, safety, and potential misuse. To address these issues, recent works have proposed to control…

Machine Learning · Computer Science 2024-11-25 Pau Rodriguez , Arno Blaas , Michal Klein , Luca Zappella , Nicholas Apostoloff , Marco Cuturi , Xavier Suau

To deliver high-quality, personalized responses, large language models (LLMs) must effectively incorporate context -- personal, demographic, and cultural information specific to an end-user. For example, asking the model to explain Newton's…

Computation and Language · Computer Science 2025-02-07 Jerry Zhi-Yang He , Sashrika Pandey , Mariah L. Schrum , Anca Dragan

Steering large language models (LLMs) is usually done by either instruction prompting or activation steering. Prompting often gives strong control, but caches guidance tokens at every layer and can clutter long interactions; activation…

Machine Learning · Computer Science 2026-05-12 Andy Zeyi Liu , Michael Zhang , Ilana Greenberg , Adam Alnasser , Lucas Baker , John Sous

Recent work in activation steering has demonstrated the potential to better control the outputs of Large Language Models (LLMs), but it involves finding steering vectors. This is difficult because engineers do not typically know how…

Computation and Language · Computer Science 2023-12-08 Ole Jorgensen , Dylan Cope , Nandi Schoots , Murray Shanahan

Safety alignment is indispensable for Large Language Models (LLMs) to defend threats from malicious instructions. However, recent researches reveal safety-aligned LLMs prone to reject benign queries due to the exaggerated safety issue,…

Artificial Intelligence · Computer Science 2024-12-18 Zouying Cao , Yifei Yang , Hai Zhao

In this paper, we investigate whether refusal behavior can be predicted from LLM intermediate activations before decoding using linear probes trained on residual stream activations at each transformer block. We find that refusal is linearly…

Artificial Intelligence · Computer Science 2026-05-28 Matteo Gioele Collu , Riccardo Conte , Alberto Giaretta , Denis Kleyko , Mauro Conti , Matteo Zavatteri , Roberto Confalonieri

Large language models (LLMs) have shown remarkable success in recent years, enabling a wide range of applications, including intelligent assistants that support users' daily life and work. A critical factor in building such assistants is…

Computation and Language · Computer Science 2025-10-28 Xiaoyan Zhao , Ming Yan , Yilun Qiu , Haoting Ni , Yang Zhang , Fuli Feng , Hong Cheng , Tat-Seng Chua

LLMs increasingly exhibit over-refusal behavior, where safety mechanisms cause models to reject benign instructions that seemingly resemble harmful content. This phenomenon diminishes utility in production applications that repeatedly rely…

Computation and Language · Computer Science 2026-04-21 Utsav Maskey , Sumit Yadav , Mark Dras , Usman Naseem

Inference-time intervention (ITI) has emerged as a promising method for steering large language model (LLM) behavior in a particular direction (e.g., improving helpfulness) by intervening on token representations without costly updates to…

Computation and Language · Computer Science 2025-07-10 Duy Nguyen , Archiki Prasad , Elias Stengel-Eskin , Mohit Bansal

Activation steering has emerged as a powerful method for guiding the behavior of generative models towards desired outcomes such as toxicity mitigation. However, most existing methods apply interventions uniformly across all inputs,…

Machine Learning · Computer Science 2025-12-04 Alex Ferrando , Xavier Suau , Jordi Gonzàlez , Pau Rodriguez