English
Related papers

Related papers: When Models Outthink Their Safety: Unveiling and M…

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

Despite the impressive performance of general-purpose large language models (LLMs), they often require fine-tuning or post-training to excel at specific tasks. For instance, large reasoning models (LRMs), such as the DeepSeek-R1 series,…

Computation and Language · Computer Science 2026-04-02 Mingjie Li , Wai Man Si , Michael Backes , Yang Zhang , Yisen Wang

Large Reasoning Models (LRMs) are designed to solve complex tasks by generating explicit reasoning traces before producing final answers. However, we reveal a critical vulnerability in LRMs -- termed Unthinking Vulnerability -- wherein the…

Computation and Language · Computer Science 2025-05-20 Zihao Zhu , Hongbao Zhang , Ruotong Wang , Ke Xu , Siwei Lyu , Baoyuan Wu

Large Language Models (LLMs) are vulnerable to jailbreak attacks that exploit weaknesses in traditional safety alignment, which often relies on rigid refusal heuristics or representation engineering to block harmful outputs. While they are…

Computation and Language · Computer Science 2025-10-01 Yuyou Zhang , Miao Li , William Han , Yihang Yao , Zhepeng Cen , Ding Zhao

Thinking mode has always been regarded as one of the most valuable modes in LLMs. However, we uncover a surprising and previously overlooked phenomenon: LLMs with thinking mode are more easily broken by Jailbreak attack. We evaluate 9 LLMs…

Computation and Language · Computer Science 2025-08-15 Fan Yang

Large reasoning models (LRMs) have recently demonstrated impressive capabilities in complex reasoning tasks by leveraging increased test-time computation and exhibiting behaviors reminiscent of human-like self-reflection. While LRMs show a…

Computation and Language · Computer Science 2025-10-21 Qingcheng Zeng , Weihao Xuan , Leyang Cui , Rob Voigt

Reasoning-enhanced large language models (RLLMs), whether explicitly trained for reasoning or prompted via chain-of-thought (CoT), have achieved state-of-the-art performance on many complex reasoning tasks. However, we uncover a surprising…

Computation and Language · Computer Science 2025-09-03 Xiaomin Li , Zhou Yu , Zhiwei Zhang , Xupeng Chen , Ziji Zhang , Yingying Zhuang , Narayanan Sadagopan , Anurag Beniwal

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

From generating headlines to fabricating news, the Large Language Models (LLMs) are typically assessed by their final outputs, under the safety assumption that a refusal response signifies safe reasoning throughout the entire process.…

Computation and Language · Computer Science 2026-02-17 Zhao Tong , Chunlin Gong , Yiping Zhang , Haichao Shi , Qiang Liu , Xingcheng Xu , Shu Wu , Xiao-Yu Zhang

Large Language Models (LLMs) have demonstrated powerful capabilities that render them valuable in different applications, including conversational AI products. It is paramount to ensure the security and reliability of these products by…

Computation and Language · Computer Science 2025-01-23 Melissa Kazemi Rad , Huy Nghiem , Andy Luo , Sahil Wadhwa , Mohammad Sorower , Stephen Rawls

The rapid development of large reasoning models (LRMs), such as OpenAI-o3 and DeepSeek-R1, has led to significant improvements in complex reasoning over non-reasoning large language models~(LLMs). However, their enhanced capabilities,…

Computers and Society · Computer Science 2025-11-18 Kaiwen Zhou , Chengzhi Liu , Xuandong Zhao , Shreedhar Jangam , Jayanth Srinivasa , Gaowen Liu , Dawn Song , Xin Eric Wang

Large Reasoning Models (LRMs) generate structured chains of thought (CoTs) before producing final answers, making them especially vulnerable to knowledge leakage through intermediate reasoning steps. Yet, the memorization of sensitive…

Artificial Intelligence · Computer Science 2026-04-07 Tuan Le , Wei Qian , Mengdi Huai

Large Language Models (LLMs) suffer from a range of vulnerabilities that allow malicious users to solicit undesirable responses through manipulation of the input text. These so-called jailbreak prompts are designed to trick the LLM into…

Computation and Language · Computer Science 2025-10-13 John Hawkins , Aditya Pramar , Rodney Beard , Rohitash Chandra

The recent surge in jailbreaking attacks has revealed significant vulnerabilities in Large Language Models (LLMs) when exposed to malicious inputs. While various defense strategies have been proposed to mitigate these threats, there has…

Computation and Language · Computer Science 2025-02-24 Tianlong Li , Zhenghua Wang , Wenhao Liu , Muling Wu , Shihan Dou , Changze Lv , Xiaohua Wang , Xiaoqing Zheng , Xuanjing Huang

Reasoning-based language models have demonstrated strong performance across various domains, with the most notable gains seen in mathematical and coding tasks. Recent research has shown that reasoning also offers significant benefits for…

Artificial Intelligence · Computer Science 2025-05-27 Makesh Narsimhan Sreedhar , Traian Rebedea , Christopher Parisien

Multimodal large reasoning models (MLRMs) are increasingly deployed for vision-language tasks that produce explicit intermediate rationales. However, reasoning traces can contain unsafe content even when the final answer is non-harmful,…

Computer Vision and Pattern Recognition · Computer Science 2025-11-27 Yuxiao Xiang , Junchi Chen , Zhenchao Jin , Changtao Miao , Haojie Yuan , Qi Chu , Tao Gong , Nenghai Yu

The increasing sophistication of large vision-language models (LVLMs) has been accompanied by advances in safety alignment mechanisms designed to prevent harmful content generation. However, these defenses remain vulnerable to sophisticated…

Cryptography and Security · Computer Science 2026-04-09 Quanchen Zou , Zonghao Ying , Moyang Chen , Wenzhuo Xu , Yisong Xiao , Yakai Li , Deyue Zhang , Dongdong Yang , Zhao Liu , Xiangzheng Zhang

Large Reasoning Models (LRMs), which autonomously produce a reasoning Chain of Thought (CoT) before producing final responses, offer a promising approach to interpreting and monitoring model behaviors. Inspired by the observation that…

Computation and Language · Computer Science 2025-07-08 Jianshuo Dong , Yujia Fu , Chuanrui Hu , Chao Zhang , Han Qiu

With the development of Large Language Models (LLMs), numerous efforts have revealed their vulnerabilities to jailbreak attacks. Although these studies have driven the progress in LLMs' safety alignment, it remains unclear whether LLMs have…

Cryptography and Security · Computer Science 2025-09-16 Yu Yan , Sheng Sun , Zhe Wang , Yijun Lin , Zenghao Duan , zhifei zheng , Min Liu , Zhiyi yin , Jianping Zhang

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