用双系统理论让大模型从思考变直觉，提升推理速度。
CogniDual Framework: Self-Training Large Language Models within a Dual-System Theoretical Framework for Improving Cognitive Tasks
- 基于人类双系统认知理论，设计自训练框架
- 模型经训练后响应更快，推理效率显著提升
- 适合研究认知机制或优化模型推理的学者
认知心理学研究感知、注意、记忆、语言、问题解决、决策和推理。卡尼曼的双系统理论揭示了人类决策过程，区分快速直觉的系统1与慢速理性的系统2。近年来，大语言模型（LLMs）在多种认知任务中已接近人类水平。然而，其是否具备类似人类的认知双系统结构仍未知。本研究提出面向大模型的 extbf{CogniDual框架}（CFLLMs），通过自训练探索模型能否从深思熟虑的推理演化为直觉式应答，模拟人类学习与掌握新知识的过程。结果揭示了模型生成回答背后的认知机制，深化了对大模型认知能力的理解。实际应用中，经自训练的模型可对特定查询提供更快响应，降低推理时的计算开销。
原文摘要 · Abstract (English)
Cognitive psychology investigates perception, attention, memory, language, problem-solving, decision-making, and reasoning. Kahneman's dual-system theory elucidates the human decision-making process, distinguishing between the rapid, intuitive System 1 and the deliberative, rational System 2. Recent advancements have positioned large language Models (LLMs) as formidable tools nearing human-level proficiency in various cognitive tasks. Nonetheless, the presence of a dual-system framework analogous to human cognition in LLMs remains unexplored. This study introduces the \textbf{CogniDual Framework for LLMs} (CFLLMs), designed to assess whether LLMs can, through self-training, evolve from deliberate deduction to intuitive responses, thereby emulating the human process of acquiring and mastering new information. Our findings reveal the cognitive mechanisms behind LLMs' response generation, enhancing our understanding of their capabilities in cognitive psychology. Practically, self-trained models can provide faster responses to certain queries, reducing computational demands during inference.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。