让AI对话系统能解释为何推荐干预策略，提升教师信任度。
Tell Me Why: Designing an Explainable LLM-based Dialogue System for Student Problem Behavior Diagnosis
- 用可解释AI技术分析对话证据，生成自然语言解释。
- 22名准教师参与测试，有解释时信任度显著提升。
- 适合教育AI、心理辅导等需透明决策的场景。
诊断学生问题行为需要教师整合多方面信息，识别行为类别并制定干预策略。尽管微调的大语言模型（LLMs）可通过多轮对话提供支持，但它们很少解释为何推荐某种策略，限制了透明度和教师信任。为此，我们提出一个基于微调大模型的可解释对话系统。该系统采用分层归因方法，结合可解释AI（xAI），识别每项建议对应的对话证据，并据此生成自然语言解释。技术评估显示，该方法在识别支持性证据方面优于基线方法。一项包含22名准教师的初步用户研究发现，获得解释的参与者对系统的信任感更高。这些结果表明，提升大模型在教育对话系统中的可解释性具有广阔前景。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。