English
Related papers

Related papers: Spherical Steering: Geometry-Aware Activation Rota…

200 papers

Large Language Models (LLMs) are widely used by software engineers for programming tasks. However, research shows that LLMs often lack a deep understanding of program semantics. Even minor changes to syntax, such as renaming variables, can…

Computation and Language · Computer Science 2025-10-06 Francesca Lucchetti , Arjun Guha

Large Language Models (LLMs), despite advances in instruction tuning, often fail to follow complex user instructions. Activation steering techniques aim to mitigate this by manipulating model internals, but have a potential risk of…

Machine Learning · Computer Science 2026-03-10 Minjae Kang , Jaehyung Kim

Recent advances in Large Language Models (LLMs) have demonstrated remarkable progress in their reasoning capabilities, such as Chain-of-Thought (CoT). Most approaches rely on CoT rationales. Previous studies have shown that LLMs often…

Computation and Language · Computer Science 2026-01-21 Kentaro Kazama , Daiki Shirafuji , Tatsuhiko Saito

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

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

Test-time compute has emerged as a powerful paradigm for improving the performance of large language models (LLMs), where generating multiple outputs or refining individual chains can significantly boost answer accuracy. However, existing…

Machine Learning · Computer Science 2025-09-26 Sheng Liu , Tianlang Chen , Pan Lu , Haotian Ye , Yizheng Chen , Lei Xing , James Zou

Large language models (LLMs) can memorize and reproduce training sequences verbatim -- a tendency that undermines both generalization and privacy. Existing mitigation methods apply interventions uniformly, degrading performance on the…

Machine Learning · Computer Science 2026-02-10 Xuanqi Zhang , Haoyang Shang , Xiaoxiao Li

Generative methods for 3D assets have recently achieved remarkable progress, yet providing intuitive and precise control over the object geometry remains a key challenge. Existing approaches predominantly rely on text or image prompts,…

Computer Vision and Pattern Recognition · Computer Science 2026-03-16 Elisabetta Fedele , Francis Engelmann , Ian Huang , Or Litany , Marc Pollefeys , Leonidas Guibas

The increasing prevalence of Large Language Models (LMs) in critical applications highlights the need for controlled language generation strategies that are not only computationally efficient but that also enjoy performance guarantees. To…

Computation and Language · Computer Science 2026-03-16 Emily Cheng , Carmen Amo Alonso

Inference-time steering is widely regarded as a lightweight and parameter-free mechanism for controlling large language model (LLM) behavior, and prior work has often suggested that simple activation-level interventions can reliably induce…

Artificial Intelligence · Computer Science 2026-03-20 Zikang Ding , Qiying Hu , Yi Zhang , Hongji Li , Junchi Yao , Hongbo Liu , Lijie Hu

Mechanistic interpretability typically relies on post-hoc analysis of trained networks. We instead adopt an interventional approach: testing hypotheses a priori by modifying architectural topology to observe training dynamics. We study…

Machine Learning · Computer Science 2026-05-05 Alper Yıldırım

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

Unsupervised text embedding has shown great power in a wide range of NLP tasks. While text embeddings are typically learned in the Euclidean space, directional similarity is often more effective in tasks such as word similarity and document…

Computation and Language · Computer Science 2019-11-05 Yu Meng , Jiaxin Huang , Guangyuan Wang , Chao Zhang , Honglei Zhuang , Lance Kaplan , Jiawei Han

Leveraging pretrained Vision-Language Models (VLMs) to map language instruction and visual observations to raw low-level actions, Vision-Language-Action models (VLAs) hold great promise for achieving general-purpose robotic systems. Despite…

Robotics · Computer Science 2025-09-30 Ji Zhang , Shihan Wu , Xu Luo , Hao Wu , Lianli Gao , Heng Tao Shen , Jingkuan Song

Measurement of task progress through explicit, actionable milestones is critical for robust robotic manipulation. This progress awareness enables a model to ground its current task status, anticipate verifiable intermediate states, and…

Robotics · Computer Science 2026-03-11 Tingjun Dai , Mingfei Han , Tingwen Du , Zhiheng Liu , Zhihui Li , Salman Khan , Jun Yu , Xiaojun Chang

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

Large language models (LLMs) can sometimes detect when they are being evaluated and adjust their behavior to appear more aligned, compromising the reliability of safety evaluations. In this paper, we show that adding a steering vector to an…

Computation and Language · Computer Science 2026-03-03 Tim Tian Hua , Andrew Qin , Samuel Marks , Neel Nanda

Modern large language models (LLMs) are typically secured by auditing data, prompts, and refusal policies, while treating the forward pass as an implementation detail. We show that intermediate activations in decoder-only LLMs form a…

Cryptography and Security · Computer Science 2025-11-24 Zhiyuan Xu , Stanislav Abaimov , Joseph Gardiner , Sana Belguith

Applying steering vectors to large language models (LLMs) is an efficient and effective model alignment technique, but we lack an interpretable explanation for how it works-- specifically, what internal mechanisms steering vectors affect…

Machine Learning · Computer Science 2026-04-10 Stephen Cheng , Sarah Wiegreffe , Dinesh Manocha

A key challenge in AI alignment is guiding large language models (LLMs) to follow desired behaviors at test time. Activation steering, which modifies internal model activations during inference, offers a potential solution. However, prior…

Machine Learning · Computer Science 2025-03-04 Reza Bayat , Ali Rahimi-Kalahroudi , Mohammad Pezeshki , Sarath Chandar , Pascal Vincent