English
Related papers

Related papers: Programming Refusal with Conditional Activation St…

200 papers

Refusal is a key safety behavior in aligned language models, yet the internal mechanisms driving refusals remain opaque. In this work, we conduct a mechanistic study of refusal in instruction-tuned LLMs using sparse autoencoders to identify…

Computation and Language · Computer Science 2025-05-30 Wei Jie Yeo , Nirmalendu Prakash , Clement Neo , Roy Ka-Wei Lee , Erik Cambria , Ranjan Satapathy

Steering has emerged as a practical approach to enable post-hoc guidance of LLMs towards enforcing a specific behavior. However, it remains largely underexplored for multimodal LLMs (MLLMs); furthermore, existing steering techniques, such…

Machine Learning · Computer Science 2025-11-04 Jayneel Parekh , Pegah Khayatan , Mustafa Shukor , Arnaud Dapogny , Alasdair Newson , Matthieu Cord

Large language models (LLMs) excel at complex reasoning when they include intermediate steps, known as "chains of thought" (CoTs). However, these rationales are often overly verbose, even for simple problems, leading to wasted context,…

Artificial Intelligence · Computer Science 2025-07-09 Seyedarmin Azizi , Erfan Baghaei Potraghloo , Massoud Pedram

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

Large Language Models (LLMs) achieve remarkable performance through pretraining on extensive data. This enables efficient adaptation to diverse downstream tasks. However, the lack of interpretability in their underlying mechanisms limits…

Computation and Language · Computer Science 2025-06-03 Xintong Wang , Jingheng Pan , Liang Ding , Longyue Wang , Longqin Jiang , Xingshan Li , Chris Biemann

Large Language Models (LLMs) exhibit impressive capabilities but often hallucinate, confidently providing incorrect answers instead of admitting ignorance. Prior work has shown that models encode linear representations of their own…

Computation and Language · Computer Science 2025-12-09 Wannan , Yang , Xinchi Qiu , Lei Yu , Yuchen Zhang , Aobo Yang , Narine Kokhlikyan , Nicola Cancedda , Diego Garcia-Olano

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

Activation steering has emerged as a promising approach for efficiently adapting large language models (LLMs) to downstream behaviors. However, most existing steering methods rely on a single static direction per task or concept, making…

Large language models (LLMs) have significantly advanced dialogue systems and role-playing agents through their ability to generate human-like text. While prior studies have shown that LLMs can exhibit distinct and consistent personalities,…

Computation and Language · Computer Science 2025-02-18 Shu Yang , Shenzhe Zhu , Liang Liu , Lijie Hu , Mengdi Li , Di Wang

Controlling the behavior of large language models (LLMs) at inference time is essential for aligning outputs with human abilities and safety requirements. \emph{Activation steering} provides a lightweight alternative to prompt engineering…

Artificial Intelligence · Computer Science 2026-01-30 Diaoulé Diallo , Katharina Dworatzyk , Sophie Jentzsch , Peer Schütt , Sabine Theis , Tobias Hecking

Model alignment with human preferences is an essential step in making Large Language Models (LLMs) helpful and consistent with human values. It typically consists of supervised fine-tuning (SFT) and reinforcement learning from human…

Computation and Language · Computer Science 2023-10-10 Yi Dong , Zhilin Wang , Makesh Narsimhan Sreedhar , Xianchao Wu , Oleksii Kuchaiev

Post-training adaptation of language models is commonly achieved through parameter updates or input-based methods such as fine-tuning, parameter-efficient adaptation, and prompting. In parallel, a growing body of work modifies internal…

Computation and Language · Computer Science 2026-04-16 Simon Ostermann , Daniil Gurgurov , Tanja Baeumel , Michael A. Hedderich , Sebastian Lapuschkin , Wojciech Samek , Vera Schmitt

In this work, we examine how targeted perturbations in the activation space of Language Models (LMs) can encode complex reasoning patterns. We inject steering vectors, derived from LM activations, into LMs during inference time and study…

Computation and Language · Computer Science 2025-03-24 Jason Zhang , Scott Viteri

Access control is a cornerstone of secure computing, yet large language models often blur role boundaries by producing unrestricted responses. We study role-conditioned refusals, focusing on the LLM's ability to adhere to access control…

Computation and Language · Computer Science 2025-10-10 Đorđe Klisura , Joseph Khoury , Ashish Kundu , Ram Krishnan , Anthony Rios

Large language models (LLMs) have recently shown strong performance as zero-shot rankers, yet their effectiveness is highly sensitive to prompt formulation, particularly role-play instructions. Prior analyses suggest that role-related…

Information Retrieval · Computer Science 2026-02-04 Yumeng Wang , Catherine Chen , Suzan Verberne

Complex social behaviors, such as empathy and strategic politeness, are widely assumed to resist the directional decomposition that makes activation steering effective for coarse attributes like sentiment or toxicity. We present STAR:…

Computation and Language · Computer Science 2026-03-18 Niranjan Chebrolu , Kokil Jaidka , Gerard Christopher Yeo

Steering language models (LMs) by modifying internal activations is a popular approach for controlling text generation. Unsupervised dictionary learning methods, e.g., sparse autoencoders, can be scaled to produce many steering vectors, but…

Computation and Language · Computer Science 2025-06-05 Jiuding Sun , Sidharth Baskaran , Zhengxuan Wu , Michael Sklar , Christopher Potts , Atticus Geiger

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

Vision Language Models (VLMs) have demonstrated impressive capabilities in integrating visual and textual information for understanding and reasoning, but remain highly vulnerable to adversarial attacks. While activation steering has…

Computer Vision and Pattern Recognition · Computer Science 2025-09-03 Sihao Wu , Gaojie Jin , Wei Huang , Jianhong Wang , Xiaowei Huang

Despite the success of Instruction Tuning (IT) in training large language models (LLMs), such models often leverage spurious or biased features learnt from their training data and can become misaligned, leading to undesired behaviours.…

Machine Learning · Computer Science 2025-06-06 Tom A. Lamb , Adam Davies , Alasdair Paren , Philip H. S. Torr , Francesco Pinto
‹ Prev 1 3 4 5 6 7 10 Next ›