English
Related papers

Related papers: UnsafeChain: Enhancing Reasoning Model Safety via …

200 papers

As large language models (LLMs) advance toward expert-level performance in engineering domains, reliable reasoning under user-specified constraints becomes critical. In circuit analysis, for example, a numerically correct solution is…

Software Engineering · Computer Science 2026-04-23 Mayank Ravishankara

Chain-of-thought (CoT) reasoning is fundamental to modern LLM architectures and represents a critical intervention point for AI safety. However, CoT reasoning may exhibit failure modes that we note as pathologies, which prevent it from…

Artificial Intelligence · Computer Science 2026-02-17 Manqing Liu , David Williams-King , Ida Caspary , Linh Le , Hannes Whittingham , Puria Radmard , Cameron Tice , Edward James Young

As the development of Large Models (LMs) progresses rapidly, their safety is also a priority. In current Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs) safety workflow, evaluation, diagnosis, and alignment are…

Chain-of-Thought (CoT) monitoring has emerged as a compelling method for detecting harmful behaviors such as reward hacking for reasoning models, under the assumption that models' reasoning processes are informative of such behaviors. In…

Machine Learning · Computer Science 2026-03-10 Nikolaus Howe , Micah Carroll

Detecting harmful AI actions is important as AI agents gain adoption. Chain-of-thought (CoT) monitoring is one method widely used to detect adversarial attacks and AI misalignment. However, attackers and misaligned models might evade CoT…

Computation and Language · Computer Science 2025-10-17 Shiyuan Guo , Henry Sleight , Fabien Roger

The growing use of Large Language Models (LLMs) for automated code generation has enhanced software development efficiency, but often at the cost of security. Generated code frequently overlooks critical concerns, leaving it vulnerable to…

Cryptography and Security · Computer Science 2026-05-26 Mohammed Kharma , Ahmed Sabbah , Mohammad Alkhanafseh , Mohammad Hammoudeh , David Mohaisen

Although large language models (LLMs) have achieved excellent performance in a variety of evaluation benchmarks, they still struggle in complex reasoning tasks which require specific knowledge and multi-hop reasoning. To improve the…

Computation and Language · Computer Science 2023-11-07 Zhipeng Chen , Kun Zhou , Beichen Zhang , Zheng Gong , Wayne Xin Zhao , Ji-Rong Wen

Safety alignment in large language models (LLMs) is primarily evaluated under open-ended generation, where models can mitigate risk by refusing to respond. In contrast, many real-world applications place LLMs in structured decision-making…

Computation and Language · Computer Science 2026-04-21 Yuheng Chen , Zhiyu Wu , Bowen Cheng , Tetsuro Takahashi

Large language models (LLMs) are now ubiquitous in everyday tools, raising urgent safety concerns about their tendency to generate harmful content. The dominant safety approach -- reinforcement learning from human feedback (RLHF) --…

Machine Learning · Computer Science 2025-09-29 Sathwik Karnik , Somil Bansal

Large Language Models (LLMs) have revolutionized natural language processing and hold immense potential for advancing Artificial Intelligence. However, the core architecture of most mainstream LLMs -- the Transformer -- has inherent…

Computation and Language · Computer Science 2024-10-21 Xiang Zhang , Dujian Ding

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) are increasingly applied in financial scenarios. However, they may produce harmful outputs, including facilitating illegal activities or unethical behavior, posing serious compliance risks. To systematically…

Computation and Language · Computer Science 2026-05-04 Yutao Hou , Yihan Jiang , Yuhan Xie , Jian Yang , Liwen Zhang , Hailiang Huang , Guanhua Chen , Yun Chen

Large language models (LLMs) often improve their performance in downstream tasks when they generate Chain of Thought reasoning text before producing an answer. We investigate how LLMs recover from errors in Chain of Thought. Through…

Artificial Intelligence · Computer Science 2024-09-04 Evelyn Yee , Alice Li , Chenyu Tang , Yeon Ho Jung , Ramamohan Paturi , Leon Bergen

Safeguarding vision-language models (VLMs) is a critical challenge, as existing methods often suffer from over-defense, which harms utility, or rely on shallow alignment, failing to detect complex threats that require deep reasoning. To…

Cryptography and Security · Computer Science 2026-04-03 Nanxi Li , Zhengyue Zhao , G. Edward Suh , Marco Pavone , Chaowei Xiao

Prepending model inputs with safety prompts is a common practice for safeguarding large language models (LLMs) against queries with harmful intents. However, the underlying working mechanisms of safety prompts have not been unraveled yet,…

Machine Learning · Computer Science 2024-06-04 Chujie Zheng , Fan Yin , Hao Zhou , Fandong Meng , Jie Zhou , Kai-Wei Chang , Minlie Huang , Nanyun Peng

As large language model (LLM) based systems take on high-stakes roles in real-world decision-making, they must reconcile competing instructions from multiple sources (e.g., model developers, users, and tools) within a single prompt context.…

Computation and Language · Computer Science 2026-02-19 Zishuo Zheng , Vidhisha Balachandran , Chan Young Park , Faeze Brahman , Sachin Kumar

Large Reasoning Models (LRMs) have demonstrated impressive performance in reasoning-intensive tasks, but they remain vulnerable to harmful content generation, particularly in the mid-to-late steps of their reasoning processes. Current…

Computation and Language · Computer Science 2026-05-07 Yuquan Wang , Mi Zhang , Yining Wang , Geng Hong , Mi Wen , Xiaoyu You , Min Yang

As the popularity of Large Language Models (LLMs) grow, combining model safety with utility becomes increasingly important. The challenge is making sure that LLMs can recognize and decline dangerous prompts without sacrificing their ability…

Computation and Language · Computer Science 2024-08-30 Ruchira Ray , Ruchi Bhalani

Synthetic chain-of-thought (CoT) traces are widely used to train large reasoning models (LRMs), improving generalization by providing step-level supervision. Yet most approaches require ground-truth labels to seed or filter these traces -…

Chain-of-Thought (CoT) prompting is widely used to elicit explicit reasoning from large language models for code (LLM4Code). However, its impact on robustness and the stability of reasoning trajectories under realistic input perturbations…

Software Engineering · Computer Science 2026-04-15 Yang Liu , Da Song , Armstrong Foundjem , Heng Li , Foutse Khomh
‹ Prev 1 8 9 10 Next ›