This study investigates the internal information flow of large language models (LLMs) while performing chain-of-thought (CoT) style reasoning. Specifically, with a particular interest in the faithfulness of the CoT explanation to LLMs' final answer, we explore (i) when the LLMs' answer is (pre)determined, especially before the CoT begins or after, and (ii) how strongly the information from CoT specifically has a causal effect on the final answer. Our experiments with controlled arithmetic tasks reveal a systematic internal reasoning mechanism of LLMs. They have not derived an answer at the moment when input was fed into the model. Instead, they compute (sub-)answers while generating the reasoning chain on the fly. Therefore, the generated reasoning chains can be regarded as faithful reflections of the model's internal computation.
Investigating CoT Monitorability in Large Reasoning Models
Provable Responsible AI and Data Analytics (PRADA) Lab(可证明负责任的人工智能与数据分析师实验室);King Abdullah University of Science and Technology(卡布斯大学);University of Georgia(佐治亚大学);University of Macau(澳门大学)
Double-Checker: Enhancing Reasoning of Slow-Thinking LLMs via Self-Critical Fine-Tuning
The Hong Kong University of Science and Technology(香港科学与技术大学);University of Electronic Science and Technology of China(电子科技大学);Dalian University of Technology(大连理工大学);University of Texas at Austin(德克萨斯大学奥斯汀分校);Zhejiang University(浙江大学);University of Oxford(牛津大学);NVIDIA(NVIDIA公司);University of Surrey(萨里大学)
EvolveNav: Empowering LLM-Based Vision-Language Navigation via Self-Improving Embodied Reasoning
Shanghai Jiao Tong University(上海交通大学);Shenzhen Campus of Sun Yat-sen University(中山大学深圳校区);Peng Cheng Laboratory(鹏城实验室);Tsinghua Shenzhen International Graduate School(清华大学深圳国际研究生院);Mohamed Bin Zayed University of Artificial Intelligence(Mohamed Bin Zayed人工智能大学);Yinwang Intelligent Technology Co.(亿维智能技术有限公司)
R-Capsule: Compressing High-Level Plans for Efficient Large Language Model Reasoning
Tianjin University(天津大学);Tencent Hunyuan(腾讯文元);Peking University(北京大学);Fudan University(复旦大学);National Engineering Research Center of Educational Big Data and the Faculty of Artificial Intelligence in Education, Central China Normal University(教育大数据国家工程研究中心和教育人工智能学院,中央财经大学)
NeuronScope: A Multi-Agent Framework for Explaining Polysemantic Neurons in Language Models
Wuhan University(武汉大学);Hong Kong Baptist University(香港 Baptist大学);New Jersey Institute of Technology(新泽西理工学院);The Chinese University of Hong Kong, Shenzhen(香港中文大学(深圳))
Advancing Multi-Step Mathematical Reasoning in Large Language Models through Multi-Layered Self-Reflection with Auto-Prompting
Luiz de Queiroz College of Agriculture University of São Paulo(圣保罗大学农业学院);School of Engineering and Sciences Tecnologico de Monterrey(蒙特雷技术学院工程与科学学院);Institute of Mathematics and Computer Sciences University of São Paulo(圣保罗大学数学与计算机科学研究所)
SRLCG: Self-Rectified Large-Scale Code Generation with Multidimensional Chain-of-Thought and Dynamic Backtracking
Beihang University(北京航空航天大学);Shandong University(山东大学);Qilu University of Technology (Shandong Academy of Sciences)(齐鲁工业大学(山东省科学院));Harbin Institute of Technology(哈尔滨工业大学)
Rethinking How to Remember: Beyond Atomic Facts in Lifelong LLM Agent Memory
TMLR Group, Hong Kong Baptist University(香港 Baptist 大学 TMLR 实验组);The University of Texas at Austin(德克萨斯大学奥斯汀分校);Shanghai Jiao Tong University(上海交通大学);Sydney AI Center, The University of Sydney(悉尼大学悉尼人工智能中心)
Discovering Knowledge Deficiencies of Language Models on Massive Knowledge Base
University of Southern California(南加州大学);University of Wisconsin–Madison(威斯康星大学麦迪逊分校);University of Washington(华盛顿大学);ZOZO Research(ZOZO研究院);Amazon(亚马逊公司);University of Rochester(罗切斯特大学)