English
Related papers

Related papers: Selective Safety Steering via Value-Filtered Decod…

200 papers

Large Language Models (LLMs) exhibit impressive performance across diverse domains but often suffer from overconfidence, limiting their reliability in critical applications. We propose SteerConf, a novel framework that systematically steers…

Computation and Language · Computer Science 2025-05-27 Ziang Zhou , Tianyuan Jin , Jieming Shi , Qing Li

Adapting billion-parameter language models to a downstream task is still costly, even with parameter-efficient fine-tuning (PEFT). We re-cast task adaptation as output-distribution alignment: the objective is to steer the output…

Computation and Language · Computer Science 2026-03-03 Senkang Hu , Xudong Han , Jinqi Jiang , Yihang Tao , Zihan Fang , Yong Dai , Sam Tak Wu Kwong , Yuguang Fang

Large language models (LLMs) have demonstrated strong capabilities in code generation, yet they remain prone to producing security vulnerabilities. Existing approaches commonly suffer from two key limitations: the scarcity of high-quality…

Cryptography and Security · Computer Science 2026-03-02 Jiazheng Quan , Xiaodong Li , Bin Wang , Guo An , Like Liu , Degen Huang , Lin Liu , Chengbin Hou

Large Vision Language Models (LVLMs) achieve strong multimodal reasoning but frequently exhibit hallucinations and incorrect responses with high certainty, which hinders their usage in high-stakes domains. Existing verbalized confidence…

Computer Vision and Pattern Recognition · Computer Science 2026-04-13 Wenyi Xiao , Xinchi Xu , Leilei Gan

Steering vectors have emerged as a lightweight and effective approach for aligning large language models (LLMs) at inference time, enabling modulation over model behaviors by shifting LLM representations towards a target behavior. However,…

Machine Learning · Computer Science 2026-04-07 Soham Gadgil , Chris Lin , Su-In Lee

Large Vision-Language Models (LVLMs) have achieved strong performance on vision-language tasks, particularly Visual Question Answering (VQA). While prior work has explored unimodal biases in VQA, the problem of selection bias in…

Computer Vision and Pattern Recognition · Computer Science 2025-09-23 Md. Atabuzzaman , Ali Asgarov , Chris Thomas

While Large Language Models (LLMs) have shown significant advancements in performance, various jailbreak attacks have posed growing safety and ethical risks. Malicious users often exploit adversarial context to deceive LLMs, prompting them…

Cryptography and Security · Computer Science 2025-08-15 Jinhwa Kim , Ian G. Harris

Large Vision-Language Models (LVLMs) exhibit powerful reasoning capabilities but suffer sophisticated jailbreak vulnerabilities. Fundamentally, aligning LVLMs is not just a safety challenge but a problem of economic efficiency. Current…

Artificial Intelligence · Computer Science 2026-03-17 Ruoxi Cheng , Haoxuan Ma , Teng Ma , Hongyi Zhang

Ensuring the safety and alignment of large language models (LLMs) with human values is crucial for generating responses that are beneficial to humanity. While LLMs have the capability to identify and avoid harmful queries, they remain…

Computation and Language · Computer Science 2024-10-22 Yihua Zhou , Xiaochuan Shi

Large language models (LLMs) excel at handling human queries, but they can occasionally generate flawed or unexpected responses. Understanding their internal states is crucial for understanding their successes, diagnosing their failures,…

Computation and Language · Computer Science 2025-02-24 Xuansheng Wu , Jiayi Yuan , Wenlin Yao , Xiaoming Zhai , Ninghao Liu

Large vision-language models (LVLMs) often hallucinate content that is fluent yet unsupported by the image, limiting their reliability in real-world deployment. We show that a key failure mode arises from route competition: even when visual…

Computer Vision and Pattern Recognition · Computer Science 2026-05-26 Zhe Cheng , Wenyu Chen , Fode Zhang , Dehuan Shen

Aligning large language models (LLMs) with human objectives is crucial for real-world applications. However, fine-tuning LLMs for alignment often suffers from unstable training and requires substantial computing resources. Test-time…

Artificial Intelligence · Computer Science 2024-11-05 Lingkai Kong , Haorui Wang , Wenhao Mu , Yuanqi Du , Yuchen Zhuang , Yifei Zhou , Yue Song , Rongzhi Zhang , Kai Wang , Chao Zhang

Fine-tuning a general-purpose large language model (LLM) for a specific domain or task has become a routine procedure for ordinary users. However, fine-tuning is known to remove the safety alignment features of the model, even when the…

Computation and Language · Computer Science 2025-06-23 Kathleen C. Fraser , Hillary Dawkins , Isar Nejadgholi , Svetlana Kiritchenko

Large Language Models (LLMs) have shown impressive performance in natural language tasks, but their outputs can exhibit undesirable attributes or biases. Existing methods for steering LLMs toward desired attributes often assume unbiased…

Computation and Language · Computer Science 2024-09-05 Zhixuan Chu , Yan Wang , Longfei Li , Zhibo Wang , Zhan Qin , Kui Ren

Generative models are often deployed to make decisions on behalf of users, such as vision-language models (VLMs) identifying which person in a room is a doctor to help visually impaired individuals. Yet, VLM decisions are influenced by the…

The dominant approach to generating from language models subject to some constraint is locally constrained decoding (LCD), incrementally sampling tokens at each time step such that the constraint is never violated. Typically, this is…

The risk of harmful content generated by large language models (LLMs) becomes a critical concern. This paper presents a systematic study on assessing and improving LLMs' capability to perform the task of \textbf{course-correction}, \ie, the…

Computation and Language · Computer Science 2024-10-29 Rongwu Xu , Yishuo Cai , Zhenhong Zhou , Renjie Gu , Haiqin Weng , Yan Liu , Tianwei Zhang , Wei Xu , Han Qiu

Multi-hop QA benchmarks frequently reward Large Language Models (LLMs) for spurious correctness, masking ungrounded or flawed reasoning steps. To shift toward rigorous reasoning, we propose SAFE, a dynamic benchmarking framework that…

Computation and Language · Computer Science 2026-04-03 Daeyong Kwon , Soyoung Yoon , Seung-won Hwang

Large Reasoning Models (LRMs) have advanced automated multi-step reasoning, but their ability to generate complex Chain-of-Thought (CoT) trajectories introduces severe privacy risks, as sensitive information may be deeply embedded…

Artificial Intelligence · Computer Science 2026-01-15 Jingjing Zhou , Gaoxiang Cong , Li Su , Liang Li

Large language models (LLMs) have demonstrated remarkable capabilities in complex reasoning tasks. However, they remain highly susceptible to jailbreak attacks that undermine their safety alignment. Existing defense mechanisms typically…

Cryptography and Security · Computer Science 2026-03-17 Yu Pan , Wenlong Yu , Tiejun Wu , Xiaohu Ye , Qiannan Si , Guangquan Xu , Bin Wu