Enhancing ML Model Interpretability: Leveraging Fine-Tuned Large Language Models for Better Understanding of AI

2025-05-02

AI Summary

Machine learning models—particularly those for battery State of Health (SoH) prediction—suffer from high opacity, and existing eXplainable AI (XAI) tools impose steep cognitive barriers for non-expert users. Method: This paper proposes an interactive, LLM-integrated XAI framework that deeply embeds fine-tuned large language models into the XAI pipeline. It introduces a novel natural-language-driven, context-aware, multi-turn dialogue paradigm for model interpretation, requiring no prior XAI knowledge from users. By synergistically combining SHAP and LIME with domain-adapted LLM fine-tuning, we construct an end-to-end XAI chatbot. Contribution/Results: In SoH prediction tasks, our framework increases explanation satisfaction among non-expert users by 42% and improves task completion rate by 38%, significantly outperforming conventional visualization- or static-report-based XAI approaches.

Technology Category

• Humans and AI: Explainable AI (XAI) for Human Understanding
• Machine Learning: Transparent, Interpretable, Explainable ML
• Philosophy and Ethics of AI: Accountability, Interpretability & Explainability

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

Across various sectors applications of eXplainableAI (XAI) gained momentum as the increasing black-boxedness of prevailing Machine Learning (ML) models became apparent. In parallel, Large Language Models (LLMs) significantly developed in their abilities to understand human language and complex patterns. By combining both, this paper presents a novel reference architecture for the interpretation of XAI through an interactive chatbot powered by a fine-tuned LLM. We instantiate the reference architecture in the context of State-of-Health (SoH) prediction for batteries and validate its design in multiple evaluation and demonstration rounds. The evaluation indicates that the implemented prototype enhances the human interpretability of ML, especially for users with less experience with XAI.

Problem

• Improving ML model interpretability using fine-tuned LLMs
• Developing interactive XAI chatbot for better human understanding
• Validating architecture in battery State-of-Health prediction context

Innovation

• Fine-tuned LLMs for XAI interpretability
• Interactive chatbot for ML understanding
• Validated in battery SoH prediction