English
Related papers

Related papers: How Does the Thinking Step Influence Model Safety?…

200 papers

The advancement of Large Reasoning Models (LRMs) has catalyzed a paradigm shift from reactive ``fast thinking'' text generation to systematic, step-by-step ``slow thinking'' reasoning, unlocking state-of-the-art performance in complex…

Artificial Intelligence · Computer Science 2026-05-25 Junyao Yang , Chen Qian , Kun Wang , Linfeng Zhang , Quanshi Zhang , Yong Liu , Dongrui Liu

Large Vision-Language Models (LVLMs) undergo safety alignment to suppress harmful content. However, current defenses predominantly target explicit malicious patterns in the input representation, often overlooking the vulnerabilities…

Cryptography and Security · Computer Science 2026-03-11 Quanchen Zou , Moyang Chen , Zonghao Ying , Wenzhuo Xu , Yisong Xiao , Deyue Zhang , Dongdong Yang , Zhao Liu , Xiangzheng Zhang

Large Language Models (LLMs) have been applied to automate cyber security activities and processes including cyber investigation and digital forensics. However, the use of such models for cyber investigation and digital forensics should…

Cryptography and Security · Computer Science 2024-04-02 Jonathan Pan , Swee Liang Wong , Xin Wei Chia , Yidi Yuan

Multimodal large language models (MLLMs) have demonstrated impressive reasoning and instruction-following capabilities, yet their expanded modality space introduces new compositional safety risks that emerge from complex text-image…

Cryptography and Security · Computer Science 2025-11-18 Xuankun Rong , Wenke Huang , Tingfeng Wang , Daiguo Zhou , Bo Du , Mang Ye

Large Language Models (LLMs), despite their impressive capabilities across domains, have been shown to be vulnerable to backdoor attacks. Prior backdoor strategies predominantly operate at the token level, where an injected trigger causes…

Cryptography and Security · Computer Science 2026-04-17 Vu Tuan Truong , Long Bao Le

Chain-of-Thought (CoT) prompting has become the de facto method to elicit reasoning capabilities from large language models (LLMs). However, to mitigate hallucinations in CoT that are notoriously difficult to detect, current methods such as…

Computation and Language · Computer Science 2025-06-06 Chengwu Liu , Ye Yuan , Yichun Yin , Yan Xu , Xin Xu , Zaoyu Chen , Yasheng Wang , Lifeng Shang , Qun Liu , Ming Zhang

Large Reasoning Models (LRMs) have shown remarkable reasoning capabilities, yet they often suffer from overthinking, expending redundant computational steps on simple problems, or underthinking, failing to explore sufficient reasoning paths…

Artificial Intelligence · Computer Science 2026-04-03 Yulin Li , Tengyao Tu , Li Ding , Junjie Wang , Huiling Zhen , Yixin Chen , Yong Li , Zhuotao Tian

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

With the integration of an additional modality, large vision-language models (LVLMs) exhibit greater vulnerability to safety risks (e.g., jailbreaking) compared to their language-only predecessors. Although recent studies have devoted…

Machine Learning · Computer Science 2025-01-07 Ziwei Zheng , Junyao Zhao , Le Yang , Lijun He , Fan Li

Here, we show that current LLM unlearning methods inherently reduce models' robustness, causing them to misbehave even when a single non-adversarial forget-token is present in the retain-query. Toward understanding underlying causes, we…

Computation and Language · Computer Science 2026-04-21 Dang Huu-Tien , Hoang Thanh-Tung , Anh Bui , Minh-Phuong Nguyen , Le-Minh Nguyen , Naoya Inoue

Large reasoning models (LRMs) often consume excessive tokens, inflating computational cost and latency. More broadly, in goal reaching sequential decision problems we often want to reach the goal quickly, and LRM reasoning can be viewed…

Machine Learning · Computer Science 2026-05-27 Alex Ayoub , Kavosh Asadi , Dale Schuurmans , Csaba Szepesvári , Karim Bouyarmane

Reasoning language models (RLMs) are increasingly used in programming. Yet, even state-of-the-art RLMs frequently introduce critical security vulnerabilities in generated code. Prior training-based approaches for secure code generation face…

Cryptography and Security · Computer Science 2026-04-07 Hao Wang , Niels Mündler , Mark Vero , Jingxuan He , Dawn Song , Martin Vechev

Large Language Models (LLMs) can acquire deceptive behaviors through backdoor attacks, where the model executes prohibited actions whenever secret triggers appear in the input. Existing safety training methods largely fail to address this…

Cryptography and Security · Computer Science 2025-10-08 Guangyu Shen , Siyuan Cheng , Xiangzhe Xu , Yuan Zhou , Hanxi Guo , Zhuo Zhang , Xiangyu Zhang

Large Reasoning Models (LRMs) have significantly enhanced their capabilities in complex problem-solving by introducing a thinking draft that enables multi-path Chain-of-Thought explorations before producing final answers. Ensuring the…

Artificial Intelligence · Computer Science 2025-05-30 Zidi Xiong , Shan Chen , Zhenting Qi , Himabindu Lakkaraju

The rapid advancement of large language models (LLMs) has demonstrated milestone success in a variety of tasks, yet their potential for generating harmful content has raised significant safety concerns. Existing safety evaluation approaches…

Computation and Language · Computer Science 2025-05-22 Tianqi Du , Zeming Wei , Quan Chen , Chenheng Zhang , Yisen Wang

Reasoning Large Language Models (RLLMs) have demonstrated impressive performance on complex tasks, largely due to the adoption of Long Chain-of-Thought (Long CoT) reasoning. However, they often exhibit overthinking -- performing unnecessary…

Computation and Language · Computer Science 2025-05-30 Keqin Peng , Liang Ding , Yuanxin Ouyang , Meng Fang , Dacheng Tao

Thinking Large Language Models (LLMs) generate explicit intermediate reasoning traces before final answers, potentially improving transparency, interpretability, and solution accuracy for code generation. However, the quality of these…

Artificial Intelligence · Computer Science 2025-11-11 Haoran Xue , Gias Uddin , Song Wang

Large Reasoning Models (LRMs) excel at solving complex problems but face an overthinking dilemma. When handling simple tasks, they often produce verbose responses overloaded with thinking tokens (e.g., wait, however). These tokens trigger…

Computation and Language · Computer Science 2025-07-01 Bowen Ding , Yuhan Chen , Futing Wang , Lingfeng Ming , Tao Lin

Scaling test-time computation with reinforcement learning (RL) has emerged as a reliable path to improve large language models (LLM) reasoning ability. Yet, outcome-based reward often incentivizes models to be overconfident, leading to…

Machine Learning · Computer Science 2026-04-28 Liaoyaqi Wang , Chunsheng Zuo , William Jurayj , Benjamin Van Durme , Anqi Liu

Previous studies proposed that the reasoning capabilities of large language models (LLMs) can be improved through self-reflection, i.e., letting LLMs reflect on their own output to identify and correct mistakes in the initial responses.…

Computation and Language · Computer Science 2025-02-18 Fengyuan Liu , Nouar AlDahoul , Gregory Eady , Yasir Zaki , Talal Rahwan