English
Related papers

Related papers: Improving Activation Steering in Language Models w…

200 papers

Large language models (LLMs) are able to generate grammatically well-formed text, but how do they encode their syntactic knowledge internally? While prior work has focused largely on binary grammatical contrasts, in this work, we study the…

Computation and Language · Computer Science 2025-09-16 Alina Klerings , Jannik Brinkmann , Daniel Ruffinelli , Simone Ponzetto

As large language models (LLMs) improve in their capacity to serve as personal AI assistants, their ability to output uniquely tailored, personalized responses that align with the soft preferences of their users is essential for enhancing…

Human-Computer Interaction · Computer Science 2025-05-15 Jessica Y. Bo , Tianyu Xu , Ishan Chatterjee , Katrina Passarella-Ward , Achin Kulshrestha , D Shin

Steering methods for language models (LMs) have gained traction as lightweight alternatives to fine-tuning, enabling targeted modifications to model activations. However, prior studies primarily report results on a few models, leaving…

Computation and Language · Computer Science 2025-04-08 Patrick Queiroz Da Silva , Hari Sethuraman , Dheeraj Rajagopal , Hannaneh Hajishirzi , Sachin Kumar

Controlling specific behaviors in large language models while preserving their general capabilities is a central challenge for safe and reliable artificial intelligence deployment. Current steering methods, such as vector addition and…

Machine Learning · Computer Science 2025-10-31 Hieu M. Vu , Tan M. Nguyen

Inference-time LLM alignment methods, particularly activation steering, offer an alternative to fine-tuning by directly modifying activations during generation. Existing methods, however, often rely on non-anticipative interventions that…

Machine Learning · Computer Science 2026-04-22 Julian Skifstad , Xinyue Annie Yang , Glen Chou

Large language models (LLMs) have demonstrated impressive capabilities in natural language understanding and generation, but controlling their behavior reliably remains challenging, especially in open-ended generation settings. This paper…

Computation and Language · Computer Science 2025-12-08 Zirui He , Mingyu Jin , Bo Shen , Ali Payani , Yongfeng Zhang , Mengnan Du

Language and vision-language models have shown impressive performance across a wide range of tasks, but their internal mechanisms remain only partly understood. In this work, we study how individual attention heads in text-generative models…

Computer Vision and Pattern Recognition · Computer Science 2026-01-15 Lorenzo Basile , Valentino Maiorca , Diego Doimo , Francesco Locatello , Alberto Cazzaniga

Activation-based steering can personalize large language models at inference time, but its effects in educational settings remain unclear. We study persona vectors for seven character traits in short-answer generation and automated scoring…

Computation and Language · Computer Science 2026-04-09 Yongchao Wu , Aron Henriksson

While the success of pre-trained language models has largely eliminated the need for high-quality static word vectors in many NLP applications, such vectors continue to play an important role in tasks where words need to be modelled in the…

Computation and Language · Computer Science 2021-05-18 Na Li , Zied Bouraoui , Jose Camacho Collados , Luis Espinosa-Anke , Qing Gu , Steven Schockaert

Controlling the behavior of Large Language Models (LLMs) remains a significant challenge due to their inherent complexity and opacity. While techniques like fine-tuning can modify model behavior, they typically require extensive…

Artificial Intelligence · Computer Science 2025-05-07 Yixiong Hao , Ayush Panda , Stepan Shabalin , Sheikh Abdur Raheem Ali

We propose a method that enables large language models (LLMs) to control embodied agents through the generation of control policies that directly map continuous observation vectors to continuous action vectors. At the outset, the LLMs…

Artificial Intelligence · Computer Science 2026-02-25 Jônata Tyska Carvalho , Stefano Nolfi

Activation steering controls language model behavior by adding directions to internal representations at inference time, but standard residual-stream steering can fail in stateful dialogue. We identify KV-cache contamination as a key…

Computation and Language · Computer Science 2026-05-15 Diancheng Kang , Zheyuan Liu , Ningshan Ma , Yue Huang , Zhaoxuan Tan , Meng Jiang

Code LLMs often default to particular programming languages and libraries under neutral prompts. We investigate whether these preferences are encoded as approximately linear directions in activation space that can be manipulated at…

Machine Learning · Computer Science 2026-03-30 Md Mahbubur Rahman , Arjun Guha , Harshitha Menon

Large Language Models (LLMs) often exhibit homogenized cultural perspectives. While the World Values Survey (WVS) provides a gold standard for mapping human values, traditional direct prompting of LLMs on WVS often fails to access the…

Computation and Language · Computer Science 2026-05-27 Trung Duc Anh Dang , Sarah Masud

As Vision Language Models (VLMs) are deployed across safety-critical applications, understanding and controlling their behavioral patterns has become increasingly important. Existing behavioral control methods face significant limitations:…

Computer Vision and Pattern Recognition · Computer Science 2025-10-01 Ravikumar Balakrishnan , Mansi Phute

Effective and reliable control over large language model (LLM) behavior is a significant challenge. While activation steering methods, which add steering vectors to a model's hidden states, are a promising approach, existing techniques…

Machine Learning · Computer Science 2025-04-03 Samuel Soo , Chen Guang , Wesley Teng , Chandrasekaran Balaganesh , Tan Guoxian , Yan Ming

We introduce Language Feedback Models (LFMs) that identify desirable behaviour - actions that help achieve tasks specified in the instruction - for imitation learning in instruction following. To train LFMs, we obtain feedback from Large…

Machine Learning · Computer Science 2024-10-11 Victor Zhong , Dipendra Misra , Xingdi Yuan , Marc-Alexandre Côté

Recent work has demonstrated the potential of contrastive steering for jailbreaking Large Language Models (LLMs). However, existing methods rely on limited and inherently biased contrastive prompts and require laborious manual tuning of…

Cryptography and Security · Computer Science 2026-05-21 Junxi Chen , Junhao Dong , Xiaohua Xie

Autonomous Driving (AD) encounters significant safety hurdles in long-tail unforeseen driving scenarios, largely stemming from the non-interpretability and poor generalization of the deep neural networks within the AD system, particularly…

Artificial Intelligence · Computer Science 2024-03-25 Yixuan Wang , Ruochen Jiao , Sinong Simon Zhan , Chengtian Lang , Chao Huang , Zhaoran Wang , Zhuoran Yang , Qi Zhu

Multi-modal large language models (MLLMs) have achieved remarkable success on complex multi-modal tasks. However, it remains insufficiently explored whether they exhibit $\textbf{modality preference}$, a tendency to favor one modality over…

Computation and Language · Computer Science 2026-02-05 Yu Zhang , Jinlong Ma , Yongshuai Hou , Xuefeng Bai , Kehai Chen , Yang Xiang , Jun Yu , Min Zhang