English
Related papers

Related papers: Refusal Falls off a Cliff: How Safety Alignment Fa…

200 papers

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 reasoning models (LRMs) generate chain-of-thought (CoT) traces before producing final outputs, introducing a dynamic internal state that may complicate control mechanisms such as refusal. Unlike instruction-tuned LLMs, where refusal…

Artificial Intelligence · Computer Science 2026-05-27 Kia-Jüng Yang , Dominik Meier , Jiachen Zhao , Terry Ruas , Bela Gipp

Large Language Models (LLMs) have demonstrated remarkable success across various NLP benchmarks. However, excelling in complex tasks that require nuanced reasoning and precise decision-making demands more than raw language proficiency--LLMs…

Computation and Language · Computer Science 2025-02-24 Ang Li , Yichuan Mo , Mingjie Li , Yifei Wang , Yisen Wang

Reasoning Large Language Models (LLMs) enable test-time scaling, with dataset-level accuracy improving as the token budget increases, motivating adaptive reasoning -- spending tokens when they improve reliability and stopping early when…

Artificial Intelligence · Computer Science 2026-05-15 Xi Wang , Anushri Suresh , Alvin Zhang , Rishi More , William Jurayj , Benjamin Van Durme , Mehrdad Farajtabar , Daniel Khashabi , Eric Nalisnick

Large language models increasingly rely on explicit chain-of-thought reasoning to solve complex tasks, yet the safety of the reasoning process itself remains largely unaddressed. Existing work focuses predominantly on content safety (i.e.,…

Artificial Intelligence · Computer Science 2026-05-07 Xunguang Wang , Yuguang Zhou , Qingyue Wang , Zongjie Li , Ruixuan Huang , Zhenlan Ji , Pingchuan Ma , Shuai Wang

From the perspective of content safety issues, alignment has shown to limit large language models' (LLMs) harmful content generation. This intentional method of reinforcing models to not respond to certain user inputs seem to be present in…

Computation and Language · Computer Science 2023-08-28 Aibek Bekbayev , Sungbae Chun , Yerzat Dulat , James Yamazaki

Reinforcement learning (RL) plays a crucial role in shaping the behavior of large language and reasoning models (LLMs/LRMs). However, it often produces brittle and unstable policies, leading to critical failures such as spurious reasoning,…

Artificial Intelligence · Computer Science 2025-07-29 Xingcheng Xu

Reasoning language models (RLMs) achieve strong performance on complex reasoning tasks, yet they still exhibit a multilingual reasoning gap, performing better in high-resource languages than in low-resource ones. While recent efforts have…

Computation and Language · Computer Science 2026-04-14 Deokhyung Kang , Seonjeong Hwang , Daehui Kim , Hyounghun Kim , Gary Geunbae Lee

Instruction-following is essential for aligning large language models (LLMs) with user intent. While recent reasoning-oriented models exhibit impressive performance on complex mathematical problems, their ability to adhere to natural…

Computation and Language · Computer Science 2025-05-27 Tingchen Fu , Jiawei Gu , Yafu Li , Xiaoye Qu , Yu Cheng

Large Reasoning Models (LRMs) achieve strong performance on complex multi-step reasoning, yet they still exhibit severe safety failures such as harmful content generation. Existing methods often apply coarse-grained constraints over the…

Artificial Intelligence · Computer Science 2026-04-27 Yingzhi Mao , Chunkang Zhang , Junxiang Wang , Xinyan Guan , Boxi Cao , Yaojie Lu , Hongyu Lin , Xianpei Han , Le Sun

Large Reasoning Models possess remarkable capabilities for self-correction in general domain; however, they frequently struggle to recover from unsafe reasoning trajectories under adversarial attacks. Existing alignment methods attempt to…

Artificial Intelligence · Computer Science 2026-05-12 Dongcheng Zhang , Yi Zhang , Yuxin Chen , An Zhang , Xiang Wang , Chaochao Lu

Large Language Models (LLMs) excel in reasoning tasks requiring a single correct answer, but they perform poorly in multi-solution tasks that require generating comprehensive and diverse answers. We attribute this limitation to…

Computation and Language · Computer Science 2025-12-02 Jiannan Guan , Qiguang Chen , Libo Qin , Dengyun Peng , Jinhao Liu , Liangyu Huo , Jian Xie , Wanxiang Che

Large language models (LLMs) possess strong semantic understanding, driving significant progress in data mining applications. This is further enhanced by large reasoning models (LRMs), which provide explicit multi-step reasoning traces. On…

Machine Learning · Computer Science 2026-04-07 Aobo Chen , Chenxu Zhao , Chenglin Miao , Mengdi Huai

Automated \enquote{LLM-as-a-Judge} frameworks have become the de facto standard for scalable evaluation across natural language processing. For instance, in safety evaluation, these judges are relied upon to evaluate harmfulness in order to…

Computation and Language · Computer Science 2026-03-17 Leo Schwinn , Moritz Ladenburger , Tim Beyer , Mehrnaz Mofakhami , Gauthier Gidel , Stephan Günnemann

Large language models (LLMs) excel in various capabilities but pose safety risks such as generating harmful content and misinformation, even after safety alignment. In this paper, we explore the inner mechanisms of safety alignment through…

Computation and Language · Computer Science 2025-10-24 Jianhui Chen , Xiaozhi Wang , Zijun Yao , Yushi Bai , Lei Hou , Juanzi Li

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

Vision-Language Models (VLMs) have achieved remarkable progress in multimodal reasoning tasks through enhanced chain-of-thought capabilities. However, this advancement also introduces novel safety risks, as these models become increasingly…

Computer Vision and Pattern Recognition · Computer Science 2025-10-22 Yinan Xia , Yilei Jiang , Yingshui Tan , Xiaoyong Zhu , Xiangyu Yue , Bo Zheng

Large Reasoning Models (LRMs), such as OpenAI o1 and DeepSeek-R1, have been rapidly progressing and achieving breakthrough performance on complex reasoning tasks such as mathematics and coding. However, the open-source R1 models have raised…

Artificial Intelligence · Computer Science 2025-04-15 Yichi Zhang , Zihao Zeng , Dongbai Li , Yao Huang , Zhijie Deng , Yinpeng Dong

For Large Language Models (LLMs) to be reliably deployed in both everyday and high-stakes domains, knowing when not to answer is equally critical as answering correctly. Real-world user queries, which can be underspecified, ill-posed, or…

Artificial Intelligence · Computer Science 2025-06-11 Polina Kirichenko , Mark Ibrahim , Kamalika Chaudhuri , Samuel J. Bell

Large language models (LLMs) have shown significant progress in reasoning tasks. However, recent studies show that transformers and LLMs fail catastrophically once reasoning problems exceed modest complexity. We revisit these findings…

Artificial Intelligence · Computer Science 2025-10-28 Revanth Rameshkumar , Jimson Huang , Yunxin Sun , Fei Xia , Abulhair Saparov