Reasoning is a distinctive human capacity, enabling us to address complex problems by breaking them down into a series of manageable cognitive steps. Yet, complex logical reasoning is still cumbersome for language models. Based on the dual process theory in cognitive science, we are the first to unravel the cognitive reasoning abilities of language models. Our framework employs an iterative methodology to construct a Cognitive Tree (CogTree). The root node of this tree represents the initial query, while the leaf nodes consist of straightforward questions that can be answered directly. This construction involves two main components: the implicit extraction module (referred to as the intuitive system) and the explicit reasoning module (referred to as the reflective system). The intuitive system rapidly generates multiple responses by utilizing in-context examples, while the reflective system scores these responses using comparative learning. The scores guide the intuitive system in its subsequent generation step. Our experimental results on two popular and challenging reasoning tasks indicate that it is possible to achieve a performance level comparable to that of GPT-3.5 (with 175B parameters), using a significantly smaller language model that contains fewer parameters (<=7B) than 5% of GPT-3.5.
CogRAG: Tackling Heterogeneous Cognitive Demands in RAG via Stratified Retrieval and Reasoning
School of Computer and Computing Science, Hangzhou City University(杭州城市大学计算机与计算科学学院);Innovation Center of Yangtze River Delta, Zhejiang University(长三角创新中心,浙江大学);Institute of Digital Twin, Eastern Institute of Technology(数字孪生研究院,东部技术研究院)
Modelling Analogies and Analogical Reasoning: Connecting Cognitive Science Theory and NLP Research
Computation, Cognition & Language Group, Idiap Research Institute(计算、认知与语言组,Idiap研究所);NLP Lab, EPFL(NLP实验室,EPFL);Psychological Methods, University of Amsterdam(心理方法,阿姆斯特丹大学);Faculty of Communication, Culture and Society and Faculty of Informatics Università della Svizzera italiana(传播、文化与社会学院和信息学院,瑞士大学)
From Recognition to Understanding: Unlocking Cognitive Time Series Reasoning with LLMs
Institute of Digital Twin, Eastern Institute of Technology(东方理工数字孪生研究所);Zhejiang University(浙江大学);Munich Center for Machine Learning, LMU(慕尼黑机器学习中心,慕尼黑大学)
Can LLMs Estimate Cognitive Complexity of Reading Comprehension Items?
Graduate School of Artificial Intelligence, POSTECH, Republic of Korea(韩国立科学技术院人工智能研究生院);Department of Computer Science and Engineering, POSTECH, Republic of Korea(韩国立科学技术院计算机科学与工程系)
Cognitive Loop of Thought: Reversible Hierarchical Markov Chain for Efficient Mathematical Reasoning
School of Computer Science and Technology, East China Normal University(1 计算机科学与技术学院,华东师范大学);School of Electronic and Electrical Engineering, Shanghai University of Engineering Science(2 电子电气工程学院,上海工程技术大学)
Deep Search with Hierarchical Meta-Cognitive Monitoring Inspired by Cognitive Neuroscience
Gaoling School of Artificial Intelligence\ University of China Beijing China;School of Information Technology;Search Applications Department, Tencent Beijing China;Beijing University of Posts;Gaoling School of Artificial Intelligence\ University of China;Search Applications Department, Tencent
PonsRAG: A Pons-Inspired RAG Bridging Cognitive Islands for Coordinated Long Narrative Reasoning
School of Future Technology, South China University of Technology(华南理工大学未来技术学院);TikTok Inc(字节跳动公司);School of Artificial Intelligence, Sun Yat-sen University(中山大学人工智能学院);School of Software Engineering, Sun Yat-sen University(中山大学软件工程学院)
ShadowCoT: Cognitive Hijacking for Stealthy Reasoning Backdoors in LLMs
School of Communication and Information Engineering, Shanghai University(上海大学通信与信息工程学院);College of Computer Science and Information Technology, IAU(国际应用技术大学计算机科学与信息学院);Center for AI Research (CAIR), University of Agder (UiA)(阿格德大学人工智能研究中心)
Cognitive Chain-of-Thought (CoCoT): Structured Multimodal Reasoning about Social Situations
Seoul National University(首尔国立大学);Human-Computer Interaction Institute, Carnegie Mellon University(人机交互研究所,卡内基梅隆大学);Language Technologies Institute, Carnegie Mellon University(语言技术研究所,卡内基梅隆大学)
Hán Dān Xué Bù (Mimicry) or Qīng Chū Yú Lán (Mastery)? A Cognitive Perspective on Reasoning Distillation in Large Language Models
School of Philosophy, Anhui University(安徽大学哲学学院);Institute of Neuroscience, Chinese Academy of Sciences(中国科学院神经科学研究所);Faculty of Education, University of Cambridge(剑桥大学教育学院);School of Foreign Studies, South China Normal University(华南师范大学外语学院);Division of Psychology and Language Sciences, University College London(伦敦大学学院心理学与语言科学系)
CogAtom: From Cognitive Atoms to Olympiad-level Mathematical Reasoning in Large Language Models
School of Computer Science and Engineering, Beihang University, China(北京航空航天大学计算机科学与工程学院);Meituan Inc.(美团公司);Beijing Institute for General Artificial Intelligence, China(北京通用人工智能研究院)
Whose Morality Do They Speak? Unraveling Cultural Bias in Multilingual Language Models
Research Center Trustworthy Data Science and Security of the University Alliance Ruhr(鲁尔大学联盟可信数据科学与安全研究中心);Faculty of Informatics, Technical University Dortmund(多特蒙德工业大学信息学院)
Incentivizing Dual Process Thinking for Efficient Large Language Model Reasoning
Gaoling School of Artificial Intelligence, Renmin University of China(中国人民大学人工智能学院);Department of Computer Science, National University of Singapore(新加坡国立大学计算机科学系);Ant Group(蚂蚁集团)