English
Related papers

Related papers: SOM Directions are Better than One: Multi-Directio…

200 papers

Jailbreaks have been a central focus of research regarding the safety and reliability of large language models (LLMs), yet the mechanisms underlying these attacks remain poorly understood. While previous studies have predominantly relied on…

Cryptography and Security · Computer Science 2025-11-04 Nathalie Kirch , Constantin Weisser , Severin Field , Helen Yannakoudakis , Stephen Casper

This paper presents a systematic evaluation of Large Language Models' (LLMs) behavior on long-tail distributed (encrypted) texts and their safety implications. We introduce a two-dimensional framework for assessing LLM safety: (1)…

Computation and Language · Computer Science 2025-06-05 Utsav Maskey , Mark Dras , Usman Naseem

Extensive work has been devoted to improving the safety mechanism of Large Language Models (LLMs). However, LLMs still tend to generate harmful responses when faced with malicious instructions, a phenomenon referred to as "Jailbreak…

Computation and Language · Computer Science 2024-02-26 Yanrui Du , Sendong Zhao , Ming Ma , Yuhan Chen , Bing Qin

Current LLM-based driving agents that rely on unstructured plain-text memory suffer from low-precision scene retrieval and inefficient reflection. To address this limitation, we present RESPOND, a structured decision-making framework for…

Human-Computer Interaction · Computer Science 2025-12-24 Dan Chen , Heye Huang , Tiantian Chen , Zheng Li , Yongji Li , Yuhui Xu , Sikai Chen

Reward models (RMs) play a central role in aligning large language models (LLMs) with human preferences. However, RMs are often sensitive to spurious features such as response length. Existing inference-time approaches for mitigating these…

Computation and Language · Computer Science 2026-05-01 Kazutoshi Shinoda , Kosuke Nishida , Kyosuke Nishida

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

Safety-trained language models routinely refuse requests for help circumventing rules. But not all rules deserve compliance. When users ask for help evading rules imposed by an illegitimate authority, rules that are deeply unjust or absurd…

Artificial Intelligence · Computer Science 2026-04-09 Cameron Pattison , Lorenzo Manuali , Seth Lazar

Large Language Models (LLMs) are widely deployed in diverse real-world settings, yet remain vulnerable to jailbreaking, where prompt-based attacks bypass safety filters. We present THREAT (Targeted Harmful generation via Reframing and…

Cryptography and Security · Computer Science 2026-05-22 Shahnewaz Karim Sakib , Swati Kar , Anindya Bijoy Das

Aligned language models refuse harmful instructions, but the representations through which they recognise such instructions are less well characterised than the behaviours they produce. Harmful intent is linearly separable from…

Machine Learning · Computer Science 2026-05-12 Isaac Llorente-Saguer

Temporal Table Reasoning is a critical challenge for Large Language Models (LLMs), requiring effective reasoning to extract relevant insights. Despite existence of multiple prompting methods, their impact on table reasoning remains largely…

Computation and Language · Computer Science 2025-08-11 Abhishek Rajgaria , Kushagra Dixit , Mayank Vyas , Harshavardhan Kalalbandi , Dan Roth , Vivek Gupta

Refusal behavior by Large Language Models is increasingly visible in content moderation, yet little is known about how refusals vary by the identity of the user making the request. This study investigates refusal as a sociotechnical outcome…

Computer Vision and Pattern Recognition · Computer Science 2025-10-28 Sha Luo , Sang Jung Kim , Zening Duan , Kaiping Chen

Large Language Models (LLMs) unlearning is crucial for removing hazardous or privacy-leaking information from the model. Practical LLM unlearning demands satisfying multiple challenging objectives simultaneously: removing undesirable…

Machine Learning · Computer Science 2026-04-20 Yisheng Zhong , Sijia Liu , Zhuangdi Zhu

When one agent interacts with a multi-agent environment, it is challenging to deal with various opponents unseen before. Modeling the behaviors, goals, or beliefs of opponents could help the agent adjust its policy to adapt to different…

Machine Learning · Computer Science 2022-06-22 Xiaopeng Yu , Jiechuan Jiang , Wanpeng Zhang , Haobin Jiang , Zongqing Lu

Continual unlearning poses the challenge of enabling large vision-language models to selectively refuse specific image-instruction pairs in response to sequential deletion requests, while preserving general utility. However, sequential…

Computer Vision and Pattern Recognition · Computer Science 2026-03-24 Hyundong Jin , Dongyoon Han , Eunwoo Kim

With the rapid advancement of large language models (LLMs), the safety of LLMs has become a critical concern. Despite significant efforts in safety alignment, current LLMs remain vulnerable to jailbreaking attacks. However, the root causes…

Artificial Intelligence · Computer Science 2026-03-10 Yonghong Deng , Zhen Yang , Ping Jian , Xinyue Zhang , Zhongbin Guo , Chengzhi Li

Large Language Models (LLMs) remain susceptible to jailbreak exploits that bypass safety filters and induce harmful or unethical behavior. This work presents a systematic taxonomy of existing jailbreak defenses across prompt-level,…

Cryptography and Security · Computer Science 2025-11-25 Ryan Wong , Hosea David Yu Fei Ng , Dhananjai Sharma , Glenn Jun Jie Ng , Kavishvaran Srinivasan

We propose cognitive prompting as a novel approach to guide problem-solving in large language models (LLMs) through structured, human-like cognitive operations, such as goal clarification, decomposition, filtering, abstraction, and pattern…

Computation and Language · Computer Science 2024-12-03 Oliver Kramer , Jill Baumann

Iterative jailbreak methods that repeatedly rewrite and input prompts into large language models (LLMs) to induce harmful outputs -- using the model's previous responses to guide each new iteration -- have been found to be a highly…

Computation and Language · Computer Science 2025-10-21 Masahiro Kaneko , Zeerak Talat , Timothy Baldwin

We introduce Robust Multi-Objective Decoding (RMOD), a novel inference-time algorithm that robustly aligns Large Language Models (LLMs) to multiple human objectives (e.g., instruction-following, helpfulness, safety) by maximizing the…

Machine Learning · Computer Science 2026-02-17 Seongho Son , William Bankes , Sangwoong Yoon , Shyam Sundhar Ramesh , Xiaohang Tang , Ilija Bogunovic

Safety alignment has become a critical step to ensure LLMs refuse harmful requests while providing helpful and harmless responses. However, despite the ubiquity of safety alignment for deployed frontier models, two separate lines of recent…

Cryptography and Security · Computer Science 2026-04-06 John T. Halloran
‹ Prev 1 8 9 10 Next ›