English
Related papers

Related papers: InvThink: Premortem Reasoning for Safer Language M…

200 papers

Large reasoning models (LRMs) extend large language models by generating explicit chain-of-thought (CoT) reasoning, significantly improving mathematical and logical problem solving. However, this explicit reasoning process also introduces…

Computation and Language · Computer Science 2025-12-02 Jinghan Jia , Nathalie Baracaldo , Sijia Liu

Reasoning language models improve performance on complex tasks by generating long chains of thought (CoTs), but this process can also increase harmful outputs in adversarial settings. In this work, we ask whether the long CoTs can be…

Computation and Language · Computer Science 2025-10-08 Yik Siu Chan , Zheng-Xin Yong , Stephen H. Bach

Advanced reasoning in large language models has achieved remarkable performance on challenging tasks, but the prevailing long-context reasoning paradigm faces critical limitations: quadratic computational scaling with sequence length,…

Computation and Language · Computer Science 2026-02-26 Yuchen Yan , Yongliang Shen , Yang Liu , Jin Jiang , Mengdi Zhang , Jian Shao , Yueting Zhuang

Large Language Models (LLMs) often exhibit deficiencies with complex reasoning tasks, such as maths, which we attribute to the discrepancy between human reasoning patterns and those presented in the LLMs' training data. When dealing with…

Computation and Language · Computer Science 2025-08-28 Cong Liu , Wenchang Chai , Hejun Wu , Yan Pan , Pengxu Wei , Liang Lin

Vision-Language Models (VLMs) show promise for autonomous driving, yet their struggle with hallucinations, inefficient reasoning, and limited real-world validation hinders accurate perception and robust step-by-step reasoning. To overcome…

Recent advancements in large language models (LLMs) have demonstrated that fine-tuning and human alignment can render LLMs harmless. In practice, such "harmlessness" behavior is mainly achieved by training models to reject harmful requests,…

Computation and Language · Computer Science 2025-03-25 Shengyun Si , Xinpeng Wang , Guangyao Zhai , Nassir Navab , Barbara Plank

Recent work has highlighted the importance of monitoring chain-of-thought reasoning for AI safety; however, current approaches that analyze textual reasoning steps can miss subtle harmful patterns and may be circumvented by models that hide…

Artificial Intelligence · Computer Science 2025-10-22 Antonio-Gabriel Chacón Menke , Phan Xuan Tan , Eiji Kamioka

Current safety alignment techniques for large language models (LLMs) face two key challenges: (1) under-generalization, which leaves models vulnerable to novel jailbreak attacks, and (2) over-alignment, which leads to the excessive refusal…

Computation and Language · Computer Science 2025-04-15 Yutao Mou , Yuxiao Luo , Shikun Zhang , Wei Ye

Chain-of-thought (CoT) prompting enhances reasoning in large language models (LLMs) but often leads to verbose and redundant outputs, thus increasing inference cost. We hypothesize that many reasoning steps are unnecessary for producing…

Computation and Language · Computer Science 2025-09-30 Xin Liu , Lu Wang

Training Large Language Models (LLMs) for chain-of-thought reasoning presents a significant challenge: supervised fine-tuning on a single "golden" rationale hurts generalization as it penalizes equally valid alternatives, whereas…

Computation and Language · Computer Science 2025-11-14 Mingye Zhu , Yi Liu , Zheren Fu , Quan Wang , Yongdong Zhang

Recent advances in Chain-of-Thought (CoT) prompting have substantially improved the reasoning capabilities of large language models (LLMs), but have also introduced their computational efficiency as a new attack surface. In this paper, we…

Cryptography and Security · Computer Science 2025-11-17 Shuaitong Liu , Renjue Li , Lijia Yu , Lijun Zhang , Zhiming Liu , Gaojie Jin

Large language models (LLMs) exhibit exceptional capabilities across various tasks but also pose risks by generating harmful content. Existing safety mechanisms, while improving model safety, often lead to overly cautious behavior and fail…

Machine Learning · Computer Science 2025-09-16 Peixuan Han , Cheng Qian , Xiusi Chen , Yuji Zhang , Heng Ji , Denghui Zhang

Although Large Reasoning Models (LRMs) have progressed in solving complex problems, their chain-of-thought (CoT) reasoning often contains harmful content that can persist even when the final responses appear safe. We show that this issue…

Artificial Intelligence · Computer Science 2026-03-03 Yichi Zhang , Yue Ding , Jingwen Yang , Tianwei Luo , Dongbai Li , Ranjie Duan , Qiang Liu , Hang Su , Yinpeng Dong , Jun Zhu

Chain of thought finetuning (cot-finetuning) aims to endow small language models (SLM) with reasoning ability to improve their performance towards specific tasks by allowing them to imitate the reasoning procedure of large language models…

Computation and Language · Computer Science 2025-08-08 Xiaoshu Chen , Sihang Zhou , Ke Liang , Xinwang Liu

Recent studies on the safety alignment of large language models (LLMs) have revealed that existing approaches often operate superficially, leaving models vulnerable to various adversarial attacks. Despite their significance, these studies…

Cryptography and Security · Computer Science 2025-06-02 Jianwei Li , Jung-Eun Kim

Chain-of-Thought (CoT) reasoning has emerged as a key technique for eliciting complex reasoning in Large Language Models (LLMs). Although interpretable, its dependence on natural language limits the model's expressive bandwidth. Continuous…

Artificial Intelligence · Computer Science 2026-04-28 Sharan Ramjee

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

Prompt design significantly impacts the moral competence and safety alignment of large language models (LLMs), yet empirical comparisons remain fragmented across datasets and models.We introduce ProMoral-Bench, a unified benchmark…

Artificial Intelligence · Computer Science 2026-02-17 Rohan Subramanian Thomas , Shikhar Shiromani , Abdullah Chaudhry , Ruizhe Li , Vasu Sharma , Kevin Zhu , Sunishchal Dev

Large Language Models (LLMs) have shown impressive performance in reasoning tasks. However, LLMs tend to generate excessively long reasoning content, leading to significant computational overhead. Our observations indicate that even on…

Computation and Language · Computer Science 2025-05-21 Guochao Jiang , Guofeng Quan , Zepeng Ding , Ziqin Luo , Dixuan Wang , Zheng Hu

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