Cognitive Activation and Chaotic Dynamics in Large Language Models: A Quasi-Lyapunov Analysis of Reasoning Mechanisms
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916655119990784 |
|---|---|
| author | Li, Xiaojian Leng, Yongkang Ding, Ruiqing Mo, Hangjie Yang, Shanlin |
| author_facet | Li, Xiaojian Leng, Yongkang Ding, Ruiqing Mo, Hangjie Yang, Shanlin |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_13530 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Cognitive Activation and Chaotic Dynamics in Large Language Models: A Quasi-Lyapunov Analysis of Reasoning Mechanisms Li, Xiaojian Leng, Yongkang Ding, Ruiqing Mo, Hangjie Yang, Shanlin Machine Learning Artificial Intelligence 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. |
| title | Cognitive Activation and Chaotic Dynamics in Large Language Models: A Quasi-Lyapunov Analysis of Reasoning Mechanisms |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2503.13530 |