大型语言模型中的认知激活与混沌动力学：推理机制的拟Lyapunov分析
Cognitive Activation and Chaotic Dynamics in Large Language Models: A Quasi-Lyapunov Analysis of Reasoning Mechanisms
AI总结：
本文提出“认知激活”理论并用拟Lyapunov指数分析LLM各层混沌特征，证明信息积累呈非线性指数规律、MLP贡献高于注意力且初值扰动显著影响推理，从而为推理可解释性与平衡创造性、可靠性提供混沌理论框架。
摘要：
大型语言模型（LLM）所展现的类人推理能力，挑战了传统神经网络理论对固定参数系统灵活性的理解。本文提出“Cognitive Activation（认知激活）”理论，从动态系统视角揭示LLM推理机制的本质：模型的推理能力源于参数空间中动态信息提取的混沌过程。通过引入Quasi-Lyapunov Exponent（QLE，拟Lyapunov指数），我们定量分析了模型在不同层的混沌特征。实验表明，模型的信息积累遵循非线性指数规律，并且Multilayer Perceptron（MLP，多层感知机）在最终输出中所占比例高于注意力机制。进一步实验表明，微小的初始值扰动会对模型的推理能力产生显著影响，证实了大型语言模型是混沌系统这一理论分析。本研究为LLM推理的可解释性提供了一个混沌理论框架，并揭示了在模型设计中平衡创造性与可靠性的潜在路径。
英文摘要：
The human-like reasoning capabilities exhibited by Large Language Models (LLMs) challenge the traditional neural network theory's understanding of the flexibility of fixed-parameter systems. This paper proposes the "Cognitive Activation" theory, revealing the essence of LLMs' reasoning mechanisms from the perspective of dynamic systems: the model's reasoning ability stems from a chaotic process of dynamic information extraction in the parameter space. By introducing the Quasi-Lyapunov Exponent (QLE), we quantitatively analyze the chaotic characteristics of the model at different layers. Experiments show that the model's information accumulation follows a nonlinear exponential law, and the Multilayer Perceptron (MLP) accounts for a higher proportion in the final output than the attention mechanism. Further experiments indicate that minor initial value perturbations will have a substantial impact on the model's reasoning ability, confirming the theoretical analysis that large language models are chaotic systems. This research provides a chaos theory framework for the interpretability of LLMs' reasoning and reveals potential pathways for balancing creativity and reliability in model design.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
