English
Related papers

Related papers: Refusal Direction is Universal Across Safety-Align…

200 papers

Refusal behavior in aligned LLMs is often viewed as model-specific, yet we hypothesize it stems from a universal, low-dimensional semantic circuit shared across models. To test this, we introduce Trajectory Replay via Concept-Basis…

Computation and Language · Computer Science 2026-01-27 Tony Cristofano

System prompts provide a lightweight yet powerful mechanism for conditioning large language models (LLMs) at inference time. While prior work has focused on English-only settings, real-world deployments benefit from having a single prompt…

Computation and Language · Computer Science 2025-12-03 Lechen Zhang , Yusheng Zhou , Tolga Ergen , Lajanugen Logeswaran , Moontae Lee , David Jurgens

LLMs increasingly exhibit over-refusal behavior, where safety mechanisms cause models to reject benign instructions that seemingly resemble harmful content. This phenomenon diminishes utility in production applications that repeatedly rely…

Computation and Language · Computer Science 2026-04-21 Utsav Maskey , Sumit Yadav , Mark Dras , Usman Naseem

Although large language models (LLMs) demonstrate impressive proficiency in various tasks, they present potential safety risks, such as `jailbreaks', where malicious inputs can coerce LLMs into generating harmful content bypassing safety…

Computation and Language · Computer Science 2025-11-26 Isack Lee , Haebin Seong

Large language models (LLMs) frequently produce false refusals, declining benign requests that contain terms resembling unsafe queries. We address this challenge by introducing two comprehensive benchmarks: the Exaggerated Safety Benchmark…

Computation and Language · Computer Science 2025-12-19 Shuzhou Yuan , Ercong Nie , Yinuo Sun , Chenxuan Zhao , William LaCroix , Michael Färber

Multi-modal large language models (MLLMs) have made significant progress, yet their safety alignment remains limited. Typically, current open-source MLLMs rely on the alignment inherited from their language module to avoid harmful…

Cryptography and Security · Computer Science 2025-04-15 Yanbo Wang , Jiyang Guan , Jian Liang , Ran He

The rapid development of Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs) has exposed vulnerabilities to various adversarial attacks. This paper provides a comprehensive overview of jailbreaking research targeting…

Computation and Language · Computer Science 2024-06-24 Siyuan Wang , Zhuohan Long , Zhihao Fan , Zhongyu Wei

Safety-aligned large language models (LLMs) often generate refusal responses to harmless queries due to the over-refusal problem. However, existing methods for mitigating over-refusal cannot maintain a low refusal ratio for harmless queries…

Computation and Language · Computer Science 2026-04-21 Yupeng Qi , Ziyu Lyu , Lixin Cui , Lu Bai , Feng Xia

With the rapid advancement of Vision Language Models (VLMs), refusal mechanisms have become a critical component for ensuring responsible and safe model behavior. However, existing refusal strategies are largely \textit{one-size-fits-all}…

Computer Vision and Pattern Recognition · Computer Science 2026-02-10 Jiaxi Yang , Shicheng Liu , Yuchen Yang , Dongwon Lee

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

Large language models (LLMs) are increasingly deployed worldwide, yet their safety alignment remains predominantly English-centric. This allows for vulnerabilities in non-English contexts, especially with low-resource languages. We…

Computation and Language · Computer Science 2026-04-27 Max Zhang , Derek Liu , Kai Zhang , Joshua Franco , Haihao Liu

Large Language Models (LLMs) encode behaviors such as refusal within their activation space, yet identifying these behaviors remains a significant challenge. Existing methods often rely on predefined refusal templates detectable in output…

Computation and Language · Computer Science 2025-06-03 Vincent Siu , Nicholas Crispino , Zihao Yu , Sam Pan , Zhun Wang , Yang Liu , Dawn Song , Chenguang Wang

Multimodal large language models (MLLMs) have become the cornerstone of today's generative AI ecosystem, sparking intense competition among tech giants and startups. In particular, an MLLM generates a text response given a prompt consisting…

Cryptography and Security · Computer Science 2024-09-09 Zedian Shao , Hongbin Liu , Yuepeng Hu , Neil Zhenqiang Gong

Large Language Models (LLMs) are increasingly vulnerable to a sophisticated form of adversarial prompting known as camouflaged jailbreaking. This method embeds malicious intent within seemingly benign language to evade existing safety…

Cryptography and Security · Computer Science 2025-09-09 Youjia Zheng , Mohammad Zandsalimy , Shanu Sushmita

Safety alignment in language models operates through two mechanistically distinct systems: refusal neurons that gate whether harmful knowledge is expressed, and concept neurons that encode the harmful knowledge itself. By targeting a single…

Computation and Language · Computer Science 2026-05-12 Hamid Kazemi , Atoosa Chegini , Maria Safi

Large Language Models (LLMs) rely on safety alignment to obey safe requests while refusing harmful ones. However, traditional refusal mechanisms often lead to "rigid rejection," where a general template (e.g., "I cannot fulfill this…

Computation and Language · Computer Science 2026-05-11 Ying Zhang , Congyu Qiao , Xin Geng , Ning Xu

Large language models (LLMs) have achieved impressive performance across natural language tasks and are increasingly deployed in real-world applications. Despite extensive safety alignment efforts, recent studies show that such alignment is…

Artificial Intelligence · Computer Science 2026-02-02 Yinzhi Zhao , Ming Wang , Shi Feng , Xiaocui Yang , Daling Wang , Yifei Zhang

Evaluating aligned large language models' (LLMs) ability to recognize and reject unsafe user requests is crucial for safe, policy-compliant deployments. Existing evaluation efforts, however, face three limitations that we address with…

Large language models demonstrate powerful capabilities across various natural language processing tasks, yet they also harbor safety vulnerabilities. To enhance LLM safety, various jailbreak defense methods have been proposed to guard…

Cryptography and Security · Computer Science 2025-11-25 Junbo Zhang , Ran Chen , Qianli Zhou , Xinyang Deng , Wen Jiang

This paper provides a systematic survey of jailbreak attacks and defenses on Large Language Models (LLMs) and Vision-Language Models (VLMs), emphasizing that jailbreak vulnerabilities stem from structural factors such as incomplete training…

Cryptography and Security · Computer Science 2026-01-08 Zejian Chen , Chaozhuo Li , Chao Li , Xi Zhang , Litian Zhang , Yiming He