In recent years, the detection of AI-generated text has become a critical area of research due to concerns about academic integrity, misinformation, and ethical AI deployment. This paper presents COT Fine-tuned, a novel framework for detecting AI-generated text and identifying the specific language model. responsible for generating the text. We propose a dual-task approach, where Task A involves classifying text as AI-generated or human-written, and Task B identifies the specific LLM behind the text. The key innovation of our method lies in the use of Chain-of-Thought reasoning, which enables the model to generate explanations for its predictions, enhancing transparency and interpretability. Our experiments demonstrate that COT Fine-tuned achieves high accuracy in both tasks, with strong performance in LLM identification and human-AI classification. We also show that the CoT reasoning process contributes significantly to the models effectiveness and interpretability.
MERIT: Memory-Enhanced Retrieval for Interpretable Knowledge Tracing
School of Computer Science and Technology, East China Normal University（东华师范大学计算机科学与技术学院）；Shanghai Innovation Institute（上海创新研究院）；WeChat AI, Tencent（微信AI，腾讯）
Detecting Unfaithful Chain-of-Thought via Circuit-Guided Internal-External Discrepancy
Jilin University（吉林大学）；University of Central Florida（中央佛罗里达大学）；Arizona State University（亚利桑那州立大学）；University of Vienna（维也纳大学）；University of North Carolina at Chapel Hill（北卡罗来纳大学教堂山分校）
Data Science Section, IT University of Copenhagen（丹麦哥本哈根技术大学数据科学部门）；MaiNLP, Center for Information and Language Processing, LMU Munich（慕尼黑大学信息与语言处理中心MaiNLP）；Department of Applied Mathematics and Computer Science, Technical University of Denmark（丹麦技术大学应用数学与计算机科学系）；Pioneer Centre for Artificial Intelligence（先锋人工智能中心）；Munich Center for Machine Learning (MCML)（慕尼黑机器学习中心（MCML））
Understanding Reasoning in Chain-of-Thought from the Hopfieldian View
King Abdullah University of Science and Technology（阿卜杜拉国王科技大学）；Soochow University（苏州大学）；University of Southampton（南安普顿大学）；Arizona State University（亚利桑那州立大学）
Neural-Symbolic Knowledge Tracing: Injecting Educational Knowledge into Deep Learning for Responsible Learner Modelling
Tallinn University（塔林大学）；University of Jyväskylä（于韦斯屈莱大学）；Czech Technical University（捷克技术大学）；Kangwon National University（江原大学）；University College London（伦敦大学学院）；The University of Hong Kong（香港大学）；Monash University（莫纳什大学）；University of Central Florida（中佛罗里达大学）
Cognition-Oriented Emotion Tracing from Causes to Consequences in Real-World Social Scenes
National University of Singapore（新加坡国立大学）；School of Computing, National University of Singapore（新加坡国立大学计算机学院）；University of Oxford（牛津大学）；Institute of Computing and Intelligence, Harbin Institute of Technology (Shenzhen)（哈尔滨工业大学（深圳）计算与智能研究院）
Chain Of Thought Compression: A Theoretical Analysis
School of Computer and Information Technology, Shanxi University, Taiyuan, Shanxi, China（山西大学计算机与信息学院）；Queen Mary, University of London, UK（伦敦大学女王学院）；School of Informatics, University of Edinburgh, UK（爱丁堡大学信息学院）
Masked Thought: Simply Masking Partial Reasoning Steps Can Improve Mathematical Reasoning Learning of 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）；Alibaba Group（阿里巴巴集团）；Computational Bioscience Research Center, KAUST（阿卜杜拉国王科技大学计算生物科学研究中心）
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）
Focus on Your Question! Interpreting and Mitigating Toxic CoT Problems in Commonsense Reasoning
School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；Hunan Normal University（湖南师范大学）
The past decade has witnessed dramatic gains in natural language processing and an unprecedented scaling of large language models. These developments have been accelerated by the advent of few-shot techniques such as chain of thought (CoT) prompting. Specifically, CoT pushes the performance of large language models in a few-shot setup by augmenting the prompts with intermediate steps. Despite impressive results across various tasks, the reasons behind their success have not been explored. This work uses counterfactual prompting to develop a deeper understanding of CoT-based few-shot prompting …
RALL-E: Robust Codec Language Modeling with Chain-of-Thought Prompting for Text-to-Speech Synthesis
Microsoft（微软公司）；The University of Tokyo（东京大学）；Zhejiang University（浙江大学）；University of Science and Technology of China（中国科学技术大学）；The Chinese University of Hong Kong（香港中文大学）；The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））
Reasoning in Conversation: Solving Subjective Tasks through Dialogue Simulation for Large Language Models
Department of Computer Science and Technology, Tsinghua University（清华大学计算机科学与技术系）；Institute for AI Industry Research (AIR), Tsinghua University（清华大学人工智能产业研究院）
Tsinghua University（清华大学）；Institute for Artificial Intelligence（人工智能研究院）；State Key Lab of Intelligent Technology and Systems（智能技术与系统国家重点实验室）；Beijing National Research Center for Information Science and Technology（北京信息科学与技术国家研究中心）
Given that rich information is hidden behind ubiquitous numbers in text, numerical reasoning over text should be an essential skill of AI systems. To derive precise equations to solve numerical reasoning problems, previous work focused on modeling the structures of equations, and has proposed various structured decoders. Though structure modeling proves to be effective, these structured decoders construct a single equation in a pre-defined autoregressive order, potentially placing an unnecessary restriction on how a model should grasp the reasoning process. Intuitively, humans may have numerou…
