Unveiling LLM Mechanisms Through Neural ODEs and Control Theory

ACL ARR 2025 February Submission5908 Authors

Abstract: This paper proposes a framework combining Neural Ordinary Differential Equations (Neural ODEs) and robust control theory to enhance the interpretability and control of large language models (LLMs). By utilizing Neural ODEs to model the dynamic evolution of input-output relationships and introducing control mechanisms to optimize output quality, we demonstrate the effectiveness of this approach across multiple question-answer datasets. Experimental results show that the integration of Neural ODEs and control theory significantly improves output consistency and model interpretability, advancing the development of explainable AI technologies.

Paper Type: Long

Research Area: Interpretability and Analysis of Models for NLP

Research Area Keywords: LLM Interpretability,Neural Ordinary Differential Equations (Neural ODEs),Control theory

Contribution Types: Model analysis & interpretability, Theory

Languages Studied: English

Submission Number: 5908