English
Related papers

Related papers: AlphaSteer: Learning Refusal Steering with Princip…

200 papers

Ensuring Large Language Model (LLM) safety remains challenging due to the absence of universal standards and reliable content validators, making it difficult to obtain effective training signals. We discover that aligned models already…

Artificial Intelligence · Computer Science 2025-10-02 Guobin Shen , Dongcheng Zhao , Haibo Tong , Jindong Li , Feifei Zhao , Yi Zeng

Agile maneuvering of the quadrotor cable-suspended system is significantly hindered by its non-smooth hybrid dynamics. While model-free Reinforcement Learning (RL) circumvents explicit differentiation of complex models, achieving…

Robotics · Computer Science 2026-03-12 Dongcheng Cao , Jin Zhou , Shuo Li

Researchers have been studying approaches to steer the behavior of Large Language Models (LLMs) and build personalized LLMs tailored for various applications. While fine-tuning seems to be a direct solution, it requires substantial…

Computation and Language · Computer Science 2024-07-31 Yuanpu Cao , Tianrong Zhang , Bochuan Cao , Ziyi Yin , Lu Lin , Fenglong Ma , Jinghui Chen

Inverse reinforcement learning (IRL) enables an agent to learn complex behavior by observing demonstrations from a (near-)optimal policy. The typical assumption is that the learner's goal is to match the teacher's demonstrated behavior. In…

Machine Learning · Computer Science 2019-10-30 Sebastian Tschiatschek , Ahana Ghosh , Luis Haug , Rati Devidze , Adish Singla

Large language models (LLMs) exhibit exceptional capabilities across various tasks but also pose risks by generating harmful content. Existing safety mechanisms, while improving model safety, often lead to overly cautious behavior and fail…

Machine Learning · Computer Science 2025-09-16 Peixuan Han , Cheng Qian , Xiusi Chen , Yuji Zhang , Heng Ji , Denghui Zhang

Safe exploration is a challenging and important problem in model-free reinforcement learning (RL). Often the safety cost is sparse and unknown, which unavoidably leads to constraint violations -- a phenomenon ideally to be avoided in…

Machine Learning · Computer Science 2022-10-13 Aivar Sootla , Alexander I. Cowen-Rivers , Jun Wang , Haitham Bou Ammar

We investigate empathy-in-action -- the willingness to sacrifice task efficiency to address human needs -- as a linear direction in LLM activation space. Using contrastive prompts grounded in the Empathy-in-Action (EIA) benchmark, we test…

Computation and Language · Computer Science 2025-11-24 Juan P. Cadile

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

Large language models (LLMs) are increasingly paired with activation-based monitoring to detect and prevent harmful behaviors that may not be apparent at the surface-text level. However, existing activation safety approaches, trained on…

Artificial Intelligence · Computer Science 2026-05-01 Shir Rozenfeld , Rahul Pankajakshan , Itay Zloczower , Eyal Lenga , Gilad Gressel , Yisroel Mirsky

We address the challenge of societal bias in Large Language Models (LLMs), focusing on the Llama 2 7B Chat model. As LLMs are increasingly integrated into decision-making processes with substantial societal impact, it becomes imperative to…

Computation and Language · Computer Science 2024-02-02 Dawn Lu , Nina Rimsky

Large Language Models (LLMs) trained for average correctness often exhibit mode collapse, producing narrow decision behaviors on tasks where multiple responses may be reasonable. This limitation is particularly problematic in ordinal…

Artificial Intelligence · Computer Science 2026-02-04 Eric Yang , Jong Ha Lee , Jonathan Amar , Elissa Ye , Yugang Jia

Gradient optimization-based adversarial attack methods automate the learning of adversarial triggers to generate jailbreak prompts or leak system prompts. In this work, we take a closer look at the optimization objective of adversarial…

Machine Learning · Computer Science 2025-11-21 Zhe Wang , Yanjun Qi

Structural vibrations induced by external excitations pose significant risks, including safety hazards for occupants, structural damage, and increased maintenance costs. While conventional model-based control strategies, such as Linear…

Machine Learning · Computer Science 2025-10-03 Rohan Vitthal Thorat , Juhi Singh , Rajdip Nayek

Safe reinforcement learning (RL) seeks to mitigate unsafe behaviors that arise from exploration during training by reducing constraint violations while maintaining task performance. Existing approaches typically rely on a single policy to…

Robotics · Computer Science 2026-05-12 Murad Dawood , Usama Ahmed Siddiquie , Shahram Khorshidi , Maren Bennewitz

Changing the behavior of large language models (LLMs) can be as straightforward as editing the Transformer's residual streams using appropriately constructed "steering vectors." These modifications to internal neural activations, a form of…

Computation and Language · Computer Science 2025-05-20 Jian-Qiao Zhu , Haijiang Yan , Thomas L. Griffiths

Jailbreak attacks pose a serious threat to the safety of Large Language Models (LLMs) by crafting adversarial prompts that bypass alignment mechanisms, causing the models to produce harmful, restricted, or biased content. In this paper, we…

Machine Learning · Computer Science 2025-08-22 Xiangman Li , Xiaodong Wu , Qi Li , Jianbing Ni , Rongxing Lu

We propose a method for confidence estimation in retrieval-augmented generation (RAG) systems that aligns closely with the correctness of large language model (LLM) outputs. Confidence estimation is especially critical in high-stakes…

Computation and Language · Computer Science 2025-10-17 Zhiqi Huang , Vivek Datla , Chenyang Zhu , Alfy Samuel , Daben Liu , Anoop Kumar , Ritesh Soni

While significant attention has been dedicated to exploiting weaknesses in LLMs through jailbreaking attacks, there remains a paucity of effort in defending against these attacks. We point out a pivotal factor contributing to the success of…

Computation and Language · Computer Science 2024-06-13 Zhexin Zhang , Junxiao Yang , Pei Ke , Fei Mi , Hongning Wang , Minlie Huang

Safety detection models require examples of HHH (Helpful, Harmless, Honest)-violating outputs for robust generalization, however such examples are scarce. Activation Steering (AS) has emerged as a data-efficient method for generating…

Machine Learning · Computer Science 2026-05-28 Vijeta Deshpande , Tootiya Giyahchi , Veena Padmanabhan , Leman Akoglu , Anna Rumshisky

Safety-aligned large language models (LLMs) remain vulnerable to backdoor attacks. Recent model editing-based approaches enable efficient backdoor injection by directly modifying a small set of parameters to map triggers to attacker-desired…

Computation and Language · Computer Science 2026-03-25 Houcheng Jiang , Zetong Zhao , Junfeng Fang , Haokai Ma , Ruipeng Wang , Xiang Wang , Xiangnan He , Yang Deng
‹ Prev 1 8 9 10 Next ›