告诉我原因：设计一个可解释的基于LLM的对话系统用于学生问题行为诊断
Tell Me Why: Designing an Explainable LLM-based Dialogue System for Student Problem Behavior Diagnosis
AI总结：
本文提出基于LLM的可解释对话系统，通过层次归因方法生成自然语言解释，提升教育对话系统中LLM的可解释性，实验证明其在识别支持证据方面优于基线方法。
摘要：
诊断学生问题行为需要教师综合多方面信息，识别行为类别并制定干预策略。尽管微调的大型语言模型（LLM）可通过多轮对话支持此过程，但它们很少解释为何推荐策略，限制了透明度和教师信任。为解决此问题，我们提出一个基于微调LLM的可解释对话系统。该系统使用基于可解释AI（xAI）的层次归因方法，识别每个推荐的对话证据并基于该证据生成自然语言解释。在技术评估中，该方法在识别支持证据方面优于基线方法。在与22名预服务教师的初步用户研究中，接受解释的参与者对系统的信任度更高。这些发现表明，改进教育对话系统中LLM可解释性具有前景。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
