English
Related papers

Related papers: COSMIC: Generalized Refusal Direction Identificati…

200 papers

The successful integration of large language models (LLMs) into recommendation systems has proven to be a major breakthrough in recent studies, paving the way for more generic and transferable recommendations. However, LLMs struggle to…

Information Retrieval · Computer Science 2023-11-29 Junyan Qiu , Haitao Wang , Zhaolin Hong , Yiping Yang , Qiang Liu , Xingxing Wang

Large Language Models (LLMs) often produce fluent yet factually incorrect statements-a phenomenon known as hallucination-posing serious risks in high-stakes domains. We present Layer-wise Semantic Dynamics (LSD), a geometric framework for…

Computation and Language · Computer Science 2025-10-07 Amir Hameed Mir

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

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

Large Language Models (LLMs) often generate inconsistent responses when prompted with semantically equivalent paraphrased inputs. Recently, activation steering, a technique that modulates LLMs' behaviours by adjusting their latent…

Computation and Language · Computer Science 2025-01-23 Jingyuan Yang , Rongjun Li , Weixuan Wang , Ziyu Zhou , Zhiyong Feng , Wei Peng

A key component of building safe and reliable language models is enabling the models to appropriately refuse to follow certain instructions or answer certain questions. We may want models to output refusal messages for various categories of…

Machine Learning · Computer Science 2025-09-01 Neel Jain , Aditya Shrivastava , Chenyang Zhu , Daben Liu , Alfy Samuel , Ashwinee Panda , Anoop Kumar , Micah Goldblum , Tom Goldstein

Understanding the latent space geometry of large language models (LLMs) is key to interpreting their behavior and improving alignment. Yet it remains unclear to what extent LLMs linearly organize representations related to semantic…

Computation and Language · Computer Science 2026-01-22 Baturay Saglam , Paul Kassianik , Blaine Nelson , Sajana Weerawardhena , Yaron Singer , Amin Karbasi

Multimodal Large Language Models (MLLMs) have demonstrated exceptional capabilities in various perception and reasoning tasks. Despite this success, ensuring their reliability in practical deployment necessitates robust confidence…

Computer Vision and Pattern Recognition · Computer Science 2026-04-21 Yunkai Dang , Yifan Jiang , Yizhu Jiang , Anqi Chen , Wenbin Li , Yang Gao

LLMs have shown remarkable capabilities, but precisely controlling their response behavior remains challenging. Existing activation steering methods alter LLM behavior indiscriminately, limiting their practical applicability in settings…

Large Language Models (LLMs) exhibit a troubling duality, capable of both remarkable generalization and brittle, verbatim memorization of their training data. This unpredictability undermines their reliability in high-stakes applications.…

Computation and Language · Computer Science 2025-10-28 Xuanming Zhang

Large language models (LLMs) have demonstrated impressive language understanding and generation capabilities, enabling them to answer a wide range of questions across various domains. However, these models are not flawless and often produce…

Computation and Language · Computer Science 2024-09-23 Lang Cao

We propose affine concept editing (ACE) as an approach for steering language models' behavior by intervening directly in activations. We begin with an affine decomposition of model activation vectors and show that prior methods for steering…

Machine Learning · Computer Science 2025-01-29 Thomas Marshall , Adam Scherlis , Nora Belrose

This paper proposes a novel method for multi-lane convoy formation control that uses large language models (LLMs) to tackle coordination challenges in dynamic highway environments. Each connected and autonomous vehicle in the convoy uses a…

Multiagent Systems · Computer Science 2025-02-28 Liping Lu , Zhican He , Duanfeng Chu , Rukang Wang , Saiqian Peng , Pan Zhou

This paper presents a novel approach to enhance autonomous robotic manipulation using the Large Language Model (LLM) for logical inference, converting high-level language commands into sequences of executable motion functions. The proposed…

Robotics · Computer Science 2023-08-30 Haokun Liu , Yaonan Zhu , Kenji Kato , Izumi Kondo , Tadayoshi Aoyama , Yasuhisa Hasegawa

Recent advancements in Generative AI, particularly in Large Language Models (LLMs) and Large Vision-Language Models (LVLMs), offer new possibilities for integrating cognitive planning into robotic systems. In this work, we present a novel…

Robotics · Computer Science 2024-11-06 Arjun P S , Andrew Melnik , Gora Chand Nandi

Large language models (LLMs) have revolutionized numerous domains with their impressive performance but still face their challenges. A predominant issue is the propensity for these models to generate non-existent facts, a concern termed…

Computation and Language · Computer Science 2024-06-10 Hanning Zhang , Shizhe Diao , Yong Lin , Yi R. Fung , Qing Lian , Xingyao Wang , Yangyi Chen , Heng Ji , Tong Zhang

Large language models (LLMs) often respond confidently to questions even when they lack the necessary information, leading to hallucinated answers. In this work, we study the problem of (un)answerability detection, focusing on extractive…

Computation and Language · Computer Science 2025-09-29 Maor Juliet Lavi , Tova Milo , Mor Geva

In self-supervised contrastive learning, a widely-adopted objective function is InfoNCE, which uses the heuristic cosine similarity for the representation comparison, and is closely related to maximizing the Kullback-Leibler (KL)-based…

Machine Learning · Computer Science 2024-02-16 Yiwei Lu , Guojun Zhang , Sun Sun , Hongyu Guo , Yaoliang Yu

Large Multimodal Reasoning Models (LMRMs) are moving into real applications, where they must be both useful and safe. Safety is especially challenging in multimodal settings: images and text can be combined to bypass guardrails, and single…

Artificial Intelligence · Computer Science 2025-10-07 Yizhuo Ding , Mingkang Chen , Qiuhua Liu , Fenghua Weng , Wanying Qu , Yue Yang , Yugang Jiang , Zuxuan Wu , Yanwei Fu , Wenqi Shao

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