English
Related papers

Related papers: REAL: Reading Out Transformer Activations for Prec…

200 papers

Recent studies have indicated that Large Language Models (LLMs) harbor an inherent understanding of truthfulness, yet often fail to consistently express it and generate false statements. This gap between "knowing" and "telling" poses a…

Computation and Language · Computer Science 2025-02-27 Tianlong Wang , Xianfeng Jiao , Yinghao Zhu , Zhongzhi Chen , Yifan He , Xu Chu , Junyi Gao , Yasha Wang , Liantao Ma

We explore the internal mechanisms of how bias emerges in large language models (LLMs) when provided with ambiguous comparative prompts: inputs that compare or enforce choosing between two or more entities without providing clear context…

Computation and Language · Computer Science 2024-10-31 Rishabh Adiga , Besmira Nushi , Varun Chandrasekaran

In this work, we explore LLM's internal representation space to identify attention heads that contain the most truthful and accurate information. We further developed the Inference Time Intervention (ITI) framework, which lets bias LLM…

Computation and Language · Computer Science 2024-06-07 Jakub Hoscilowicz , Adam Wiacek , Jan Chojnacki , Adam Cieslak , Leszek Michon , Vitalii Urbanevych , Artur Janicki

Large language models (LLMs) are prone to capturing biases from training corpus, leading to potential negative social impacts. Existing prompt-based debiasing methods exhibit instability due to their sensitivity to prompt changes, while…

Computation and Language · Computer Science 2025-07-08 Yichen Li , Zhiting Fan , Ruizhe Chen , Xiaotang Gai , Luqi Gong , Yan Zhang , Zuozhu Liu

Large Language Models (LLMs) sometimes suffer from producing hallucinations, especially LLMs may generate untruthful responses despite knowing the correct knowledge. Activating the truthfulness within LLM is the key to fully unlocking LLM's…

Computation and Language · Computer Science 2024-06-06 Shaolei Zhang , Tian Yu , Yang Feng

Large language models (LLMs) can generate long-form and coherent text, yet they often hallucinate facts, which undermines their reliability. To mitigate this issue, inference-time methods steer LLM representations toward the "truthful…

Computation and Language · Computer Science 2024-06-10 Farima Fatahi Bayat , Xin Liu , H. V. Jagadish , Lu Wang

Despite significant progress in alignment, large language models (LLMs) remain vulnerable to adversarial attacks that elicit harmful behaviors. Activation steering techniques offer a promising inference-time intervention approach, but…

Machine Learning · Computer Science 2026-01-28 Quy-Anh Dang , Chris Ngo

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

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 language models (LLMs) have demonstrated significant improvements in contextual understanding. However, their ability to attend to truly critical information during long-context reasoning and generation still falls behind the pace.…

Computation and Language · Computer Science 2025-10-27 Yiju Guo , Wenkai Yang , Zexu Sun , Ning Ding , Zhiyuan Liu , Yankai Lin

Activation steering methods are widely used to control large language model (LLM) behavior and are often interpreted as revealing meaningful internal representations. This interpretation assumes that steering directions are identifiable and…

Machine Learning · Computer Science 2026-04-02 Sohan Venkatesh , Ashish Mahendran Kurapath

It is a critical challenge to efficiently unlock the powerful reasoning potential of Large Language Models (LLMs) for specific tasks or new distributions. Existing test-time adaptation methods often require tuning model parameters, which is…

Computation and Language · Computer Science 2025-12-05 Xinyue Kang , Diwei Shi , Li Chen

Techniques that learn improved representations via offline data or self-supervised objectives have shown impressive results in traditional reinforcement learning (RL). Nevertheless, it is unclear how improved representation learning can…

Computation and Language · Computer Science 2024-10-25 Vaskar Nath , Dylan Slack , Jeff Da , Yuntao Ma , Hugh Zhang , Spencer Whitehead , Sean Hendryx

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

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

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

Understanding how Transformer-based language models store and retrieve factual associations is critical for improving interpretability and enabling targeted model editing. Prior work, primarily on GPT-style models, has identified MLP…

Computation and Language · Computer Science 2025-09-11 Minyeong Choe , Haehyun Cho , Changho Seo , Hyunil Kim

Precise control over language model generation is vital for ensuring both safety and reliability. Although prompt engineering and steering are commonly used to intervene in model behaviors, the vast number of parameters in models often…

Computation and Language · Computer Science 2025-06-04 Mengru Wang , Ziwen Xu , Shengyu Mao , Shumin Deng , Zhaopeng Tu , Huajun Chen , Ningyu Zhang

While the Self-Attention mechanism in the Transformer model has proven to be effective in many domains, we observe that it is less effective in more diverse settings (e.g. multimodality) due to the varying granularity of each token and the…

Computer Vision and Pattern Recognition · Computer Science 2024-06-06 Wayner Barrios , SouYoung Jin

Solving complex, long-horizon robotic manipulation tasks requires a deep understanding of physical interactions, reasoning about their long-term consequences, and precise high-level planning. Vision-Language Models (VLMs) offer a general…

Robotics · Computer Science 2026-02-24 Yanting Yang , Shenyuan Gao , Qingwen Bu , Li Chen , Dimitris N. Metaxas