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 monitoring through ciphered reasoning: reasoning hidden in encrypted, translated, or compressed text. To assess this risk, we test whether models can perform ciphered reasoning. For each of 28 different ciphers, we fine-tune and prompt up to 10 models to reason in that cipher. We measure model accuracy on math problems as a proxy for reasoning ability. Across the models we test, we find an asymmetry: model accuracy can drop significantly when reasoning in ciphered text, even though models demonstrate comprehension of ciphered text by being able to translate it accurately to English. Even frontier models struggle with lesser-known ciphers, although they can reason accurately in well-known ciphers like rot13. We show that ciphered reasoning capability correlates with cipher prevalence in pretraining data. We also identify scaling laws showing that ciphered reasoning capability improves slowly with additional fine-tuning data. Our work suggests that evading CoT monitoring using ciphered reasoning may be an ineffective tactic for current models and offers guidance on constraining the development of this capability in future frontier models.
Towards Better Understanding of Program-of-Thought Reasoning in Cross-Lingual and Multilingual Environments
School of Information Science and Technology, VISTEC(信息科学与技术学院,VISTEC);KAIST(韩国科学技术院);Cohere;SCB 10X;AI Singapore(AI新加坡);Department of Computer Engineering, Chulalongkorn University(朱拉隆梭大学计算机工程系)
Enhancing Depression Detection with Chain-of-Thought Prompting: From Emotion to Reasoning Using Large Language Models
College of Information Science and Engineering, Ritsumeikan University(立命馆大学信息科学与工程学院);Fujita Health University(藤田医科大学);College of Computer Science and Technology, Zhejiang University(浙江大学计算机科学与技术学院)
LLMs can Find Mathematical Reasoning Mistakes by Pedagogical Chain-of-Thought
Shanghai Business School(上海商学院);Learnable.AI Inc.(Learnable.AI公司);Centre for Frontier AI Research, A*STAR(前沿人工智能研究中心,A*STAR);Institute of High-Performance Computing, A*STAR(高性能计算研究所,A*STAR);The Hong Kong Polytechnic University(香港理工大学);Microsoft Research Asia(微软亚洲研究院)
Your Models Have Thought Enough: Training Large Reasoning Models to Stop Overthinking
Shanghai Institute of Artificial Intelligence for Education, East China Normal University(华东师范大学上海智能教育研究院);School of Data Science, Fudan University(复旦大学数据科学学院);College of Computer Science and Artificial Intelligence, Fudan University(复旦大学计算机科学与人工智能学院);Antgroup(蚂蚁集团)
M$^3$CoT: A Novel Benchmark for Multi-Domain Multi-step Multi-modal Chain-of-Thought
Research Center for Social Computing and Information Retrieval(社会计算与信息检索研究中心);Harbin Institute of Technology(哈尔滨工业大学);School of Computer Science and Engineering, Central South University(中南大学计算机科学与工程学院);Shanghai AI Laboratory(上海人工智能实验室)
ChatCoT: Tool-Augmented Chain-of-Thought Reasoning on Chat-based Large Language Models
Gaoling School of Artificial Intelligence, Renmin University of China(中国人民大学高瓴人工智能学院);School of Information, Renmin University of China(中国人民大学信息学院);Beijing Key Laboratory of Big Data Management and Analysis Methods(北京大数据管理与分析方法重点实验室)
SoT: Structured-of-Thought Prompting Guides Multilingual Reasoning in Large Language Models
Key Laboratory of Big Data & Artificial Intelligence in Transportation (Beijing Jiaotong University), Ministry of Education(大数据与人工智能交通 key laboratory(北京交通大学));School of Computer Science and Technology, Beijing Jiaotong University(计算机科学与技术学院(北京交通大学));University of Montreal(蒙特利尔大学)
Self-Compression of Chain-of-Thought via Multi-Agent Reinforcement Learning
Renmin University of China(中国人民大学);Xiaohongshu Inc.(小红书公司);Institute of Automation,Chinese Academy of Sciences(中国科学院自动化研究所);University of Southern California(南加州大学);Shandong University(山东大学)
Who Sees What? Structured Thought-Action Sequences for Epistemic Reasoning in LLMs
University of Milan-Bicocca(米兰-比科卡大学);University of Essex(埃塞克斯大学);University of Naples Federico II(那不勒斯费德里科二世大学);TUM School of Social Sciences and Technology(技术与社会科学学院)