English
Related papers

Related papers: Learning to Steer: Input-dependent Steering for Mu…

200 papers

Multimodal large language models (MLLMs) have demonstrated remarkable capabilities across vision-language tasks, yet their large-scale deployment raises pressing concerns about memorized private data, outdated knowledge, and harmful…

Machine Learning · Computer Science 2026-02-03 Chenlu Ding , Jiancan Wu , Leheng Sheng , Fan Zhang , Yancheng Yuan , Xiang Wang , Xiangnan He

As Large Language Models become integral to software development, with substantial portions of AI-suggested code entering production, understanding their internal correctness mechanisms becomes critical for safe deployment. We apply sparse…

Software Engineering · Computer Science 2025-10-06 Kriz Tahimic , Charibeth Cheng

Large Language Models (LLMs) can acquire deceptive behaviors through backdoor attacks, where the model executes prohibited actions whenever secret triggers appear in the input. Existing safety training methods largely fail to address this…

Cryptography and Security · Computer Science 2025-10-08 Guangyu Shen , Siyuan Cheng , Xiangzhe Xu , Yuan Zhou , Hanxi Guo , Zhuo Zhang , Xiangyu Zhang

This work examines whether activating latent subspaces in language models (LLMs) can steer scientific code generation toward a specific programming language. Five causal LLMs were first evaluated on scientific coding prompts to quantify…

Artificial Intelligence · Computer Science 2025-06-24 Vansh Sharma , Venkat Raman

Controlling multiple behavioral attributes in large language models (LLMs) at inference time is a challenging problem due to interference between attributes and the limitations of linear steering methods, which assume additive behavior in…

Machine Learning · Computer Science 2026-04-07 Narmeen Oozeer , Luke Marks , Shreyans Jain , Fazl Barez , Amirali Abdullah

Evaluating natural language generation systems is challenging due to the diversity of valid outputs. While human evaluation is the gold standard, it suffers from inconsistencies, lack of standardisation, and demographic biases, limiting…

Computation and Language · Computer Science 2025-09-11 Hanhua Hong , Chenghao Xiao , Yang Wang , Yiqi Liu , Wenge Rong , Chenghua Lin

Autonomous driving has made significant strides through data-driven techniques, achieving robust performance in standardized tasks. However, existing methods frequently overlook user-specific preferences, offering limited scope for…

Robotics · Computer Science 2025-05-13 Chengkai Xu , Jiaqi Liu , Yicheng Guo , Yuhang Zhang , Peng Hang , Jian Sun

Even after fine-tuning and reinforcement learning, large language models (LLMs) can be difficult, if not impossible, to control reliably with prompts alone. We propose a new inference-time approach to enforcing syntactic and semantic…

Artificial Intelligence · Computer Science 2023-11-28 Alexander K. Lew , Tan Zhi-Xuan , Gabriel Grand , Vikash K. Mansinghka

Alignment in LLMs is more brittle than commonly assumed: misalignment can be triggered by adversarial prompts, benign fine-tuning, emergent misalignment, and goal misgeneralization. Recent evidence suggests that some misalignment behaviors…

Artificial Intelligence · Computer Science 2026-04-10 Niklas Herbster , Martin Zborowski , Alberto Tosato , Gauthier Gidel , Tommaso Tosato

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

Steering vectors work for some concepts and layers but fail for others, and practitioners have no way to predict which setting applies before running an intervention. We introduce the Linear Accessibility Profile (LAP), a per-layer…

Machine Learning · Computer Science 2026-04-20 Jayadev Billa

Large language models (LLMs) have achieved remarkable performance across many generation tasks. Nevertheless, effectively aligning them with desired behaviors remains a significant challenge. Activation steering is an effective and…

Computation and Language · Computer Science 2025-10-02 Zifeng Cheng , Jinwei Gan , Zhiwei Jiang , Cong Wang , Yafeng Yin , Xiang Luo , Yuchen Fu , Qing Gu

Large-scale Vision Language Models (LVLMs) exhibit advanced capabilities in tasks that require visual information, including object detection. These capabilities have promising applications in various industrial domains, such as autonomous…

Computer Vision and Pattern Recognition · Computer Science 2025-12-01 Haruki Sakajo , Hiroshi Takato , Hiroshi Tsutsui , Komei Soda , Hidetaka Kamigaito , Taro Watanabe

We show that training a single $d$-dimensional steering vector per layer with reinforcement learning, while freezing all base weights, matches the accuracy of fully RL-tuned reasoning models on mathematical-reasoning tasks. On an 8…

Pedestrian safety is a critical component of urban mobility and is strongly influenced by the interactions between pedestrian decision-making and driver yielding behavior at crosswalks. Modeling driver--pedestrian interactions at…

Computation and Language · Computer Science 2025-09-25 Yicheng Yang , Zixian Li , Jean Paul Bizimana , Niaz Zafri , Yongfeng Dong , Tianyi Li

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

MLLMs are increasingly deployed in multi-turn settings, where attackers can escalate unsafe intent through the evolving visual-text history and exploit long-context safety decay. Yet safety alignment is still dominated by single-turn data…

Machine Learning · Computer Science 2026-05-28 Haolong Hu , Hanyu Li , Tiancheng He , Huahui Yi , An Zhang , Qiankun Li , Kun Wang , Yang Liu , Zhigang Zeng

Providing high-quality feedback to Large Language Models (LLMs) on a diverse training distribution can be difficult and expensive, and providing feedback only on a narrow distribution can result in unintended generalizations. To better…

Computation and Language · Computer Science 2026-03-02 Constanza Fierro , Fabien Roger

Recent advances in Large Reasoning Models (LRMs) have demonstrated remarkable capabilities in solving complex tasks such as mathematics and coding. However, these models frequently exhibit a phenomenon known as overthinking during…

Machine Learning · Computer Science 2025-11-18 Yao Huang , Huanran Chen , Shouwei Ruan , Yichi Zhang , Xingxing Wei , Yinpeng Dong

Large Language Models (LLMs) are important tools for reasoning and problem-solving, while they often operate passively, answering questions without actively discovering new ones. This limitation reduces their ability to simulate human-like…

Computational Engineering, Finance, and Science · Computer Science 2025-09-26 Hong Su