🤖 AI Summary
This study addresses the challenge of supporting teachers in diagnosing student problem behaviors through trustworthy large language model (LLM)-based dialogue systems. While effective intervention requires integrating multidimensional information and formulating evidence-based strategies, existing LLM systems often lack explainability, undermining user trust and transparency. To bridge this gap, this work proposes an explainable dialogue system grounded in hierarchical attribution, which fine-tunes an LLM to support multi-turn diagnostic conversations and automatically generates natural language explanations that highlight the key dialogue evidence underlying each intervention recommendation. Technical evaluations demonstrate the method’s superiority over baseline approaches in identifying supportive evidence, and a user study with 22 pre-service teachers reveals that providing such explanations significantly enhances perceived system credibility. By integrating explainable AI, hierarchical attribution, and natural language generation, this research advances the development of trustworthy LLM applications in educational contexts.
📝 Abstract
Diagnosing student problem behaviors requires teachers to synthesize multifaceted information, identify behavioral categories, and plan intervention strategies. Although fine-tuned large language models (LLMs) can support this process through multi-turn dialogue, they rarely explain why a strategy is recommended, limiting transparency and teachers' trust. To address this issue, we present an explainable dialogue system built on a fine-tuned LLM. The system uses a hierarchical attribution method based on explainable AI (xAI) to identify dialogue evidence for each recommendation and generate a natural-language explanation based on that evidence. In technical evaluation, the method outperformed baseline approaches in identifying supporting evidence. In a preliminary user study with 22 pre-service teachers, participants who received explanations reported higher trust in the system. These findings suggest a promising direction for improving LLM explainability in educational dialogue systems.