English
Related papers

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

200 papers

As multimodal reasoning improves the overall capabilities of Large Vision Language Models (LVLMs), recent studies have begun to explore safety-oriented reasoning, aiming to enhance safety awareness by analyzing potential safety risks during…

Computer Vision and Pattern Recognition · Computer Science 2025-12-09 Fenghua Weng , Chaochao Lu , Xia Hu , Wenqi Shao , Wenjie Wang

Large Language Models(LLMs) have been successful in numerous fields. Alignment has usually been applied to prevent them from harmful purposes. However, aligned LLMs remain vulnerable to jailbreak attacks that deliberately mislead them into…

Cryptography and Security · Computer Science 2026-02-17 Shang Liu , Hanyu Pei , Zeyan Liu

With the increasing adoption of large language models (LLMs), ensuring the safety of LLM systems has become a pressing concern. External LLM-based guardrail models have emerged as a popular solution to screen unsafe inputs and outputs, but…

Computation and Language · Computer Science 2025-10-08 Yining She , Daniel W. Peterson , Marianne Menglin Liu , Vikas Upadhyay , Mohammad Hossein Chaghazardi , Eunsuk Kang , Dan Roth

Large Language Models (LLMs) rapidly reshape modern life, advancing fields from healthcare to education and beyond. However, alongside their remarkable capabilities lies a significant threat: the susceptibility of these models to…

Computation and Language · Computer Science 2025-05-16 Michael Fire , Yitzhak Elbazis , Adi Wasenstein , Lior Rokach

Large reasoning models (LRMs) with multi-step reasoning capabilities have shown remarkable problem-solving abilities, yet they exhibit concerning safety vulnerabilities that remain poorly understood. In this work, we investigate why safety…

Artificial Intelligence · Computer Science 2025-10-08 Qingyu Yin , Chak Tou Leong , Linyi Yang , Wenxuan Huang , Wenjie Li , Xiting Wang , Jaehong Yoon , YunXing , XingYu , Jinjin Gu

Large Language Models have found success in a variety of applications. However, their safety remains a concern due to the existence of various jailbreaking methods. Despite significant efforts, alignment and safety fine-tuning only provide…

Computation and Language · Computer Science 2025-12-16 Darpan Aswal , Céline Hudelot

Chain-of-Thought (CoT) prompting has emerged as a foundational technique for eliciting reasoning from Large Language Models (LLMs), yet the robustness of this approach to corruptions in intermediate reasoning steps remains poorly…

Computation and Language · Computer Science 2026-04-20 Ashwath Vaithinathan Aravindan , Mayank Kejriwal

Despite the outstanding performance of Large language Models (LLMs) in diverse tasks, they are vulnerable to jailbreak attacks, wherein adversarial prompts are crafted to bypass their security mechanisms and elicit unexpected responses.…

Cryptography and Security · Computer Science 2025-04-25 Zeqing He , Zhibo Wang , Zhixuan Chu , Huiyu Xu , Wenhui Zhang , Qinglong Wang , Rui Zheng

Current jailbreaking work on large language models (LLMs) aims to elicit unsafe outputs from given prompts. However, it only focuses on single-turn jailbreaking targeting one specific query. On the contrary, the advanced LLMs are designed…

Computation and Language · Computer Science 2025-08-12 Xianjun Yang , Liqiang Xiao , Shiyang Li , Faisal Ladhak , Hyokun Yun , Linda Ruth Petzold , Yi Xu , William Yang Wang

Chain-of-thought (CoT) reasoning has emerged as an effective approach for activating latent capabilities in LLMs. Interestingly, we observe that both CoT reasoning and self-training share the core objective: iteratively leveraging…

Computation and Language · Computer Science 2025-05-27 Zongqian Wu , Baoduo Xu , Ruochen Cui , Mengmeng Zhan , Xiaofeng Zhu , Lei Feng

Safety alignment incurs safety tax that perturbs a large reasoning model's (LRM) general reasoning ability. Existing datasets used for safety alignment for an LRM are usually constructed by distilling safety reasoning traces and answers…

Artificial Intelligence · Computer Science 2026-02-03 Yingsha Xie , Tiansheng Huang , Enneng Yang , Rui Min , Wenjie Lu , Xiaochun Cao , Naiqiang Tan , Li Shen

The proliferation of Large Language Models (LLMs) has revolutionized natural language processing and significantly impacted code generation tasks, enhancing software development efficiency and productivity. Notably, LLMs like GPT-4 have…

Software Engineering · Computer Science 2025-03-25 Sheng Ouyang , Yihao Qin , Bo Lin , Liqian Chen , Xiaoguang Mao , Shangwen Wang

Ensuring the safety and harmlessness of Large Language Models (LLMs) has become equally critical as their performance in applications. However, existing safety alignment methods typically suffer from safety-performance trade-offs and the…

Computation and Language · Computer Science 2025-06-30 Yichi Zhang , Siyuan Zhang , Yao Huang , Zeyu Xia , Zhengwei Fang , Xiao Yang , Ranjie Duan , Dong Yan , Yinpeng Dong , Jun Zhu

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

Self-correction has achieved impressive results in enhancing the style and security of the generated output from large language models (LLMs). However, recent studies suggest that self-correction might be limited or even counterproductive…

Computation and Language · Computer Science 2024-06-18 Che Zhang , Zhenyang Xiao , Chengcheng Han , Yixin Lian , Yuejian Fang

Large Language Models (LLMs) are typically harmless but remain vulnerable to carefully crafted prompts known as ``jailbreaks'', which can bypass protective measures and induce harmful behavior. Recent advancements in LLMs have incorporated…

Cryptography and Security · Computer Science 2024-06-03 Haibo Jin , Andy Zhou , Joe D. Menke , Haohan Wang

The discovery of "jailbreaks" to bypass safety filters of Large Language Models (LLMs) and harmful responses have encouraged the community to implement safety measures. One major safety measure is to proactively test the LLMs with…

Machine Learning · Computer Science 2025-11-10 Haibo Jin , Ruoxi Chen , Peiyan Zhang , Andy Zhou , Haohan Wang

Large language models (LLMs) can achieve highly effective performance on various reasoning tasks by incorporating step-by-step chain-of-thought (CoT) prompting as demonstrations. However, the reasoning chains of demonstrations generated by…

Computation and Language · Computer Science 2024-03-18 Jiashuo Sun , Yi Luo , Yeyun Gong , Chen Lin , Yelong Shen , Jian Guo , Nan Duan

Large language models (LLMs) are increasingly deployed in a wide range of applications, yet remain vulnerable to adversarial jailbreak attacks that circumvent their safety guardrails. Existing evaluation frameworks typically report binary…

Cryptography and Security · Computer Science 2026-05-14 Zvi Topol

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