English(EN) Tell Me Why: Designing an Explainable LLM-based Dialogue System for Student Problem Behavior Diagnosis

LLM对话系统解释建议以提高教师信任度

作者 PulseAugur 编辑部 · [2 个来源] · 2026-04-24 05:23

研究人员开发了一个使用微调的大型语言模型（LLM）的可解释对话系统，以帮助教师诊断学生的问题行为。该系统采用可解释人工智能（xAI）中的分层归因方法，识别对话中的证据并生成自然语言解释以支持其建议。一项对22名职前教师进行的初步研究表明，收到解释的教师报告称对系统的信任度有所提高。 AI

影响通过为诊断建议提供透明的推理，增强了对基于LLM的教育工具的信任。

排序理由学术论文，详细介绍了LLM对话系统的一种新的可解释人工智能方法。

AI 生成摘要 · Google Gemini · 来自 2 个来源。我们如何撰写摘要 →

报道来源 [2]

arXiv cs.CL TIER_1 English(EN) · Zhilin Fan, Deliang Wang, Penghe Chen, Yu Lu · 2026-04-27 04:00

Tell Me Why: Designing an Explainable LLM-based Dialogue System for Student Problem Behavior Diagnosis

arXiv:2604.22237v1 Announce Type: new 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 proce…
arXiv cs.CL TIER_1 English(EN) · Yu Lu · 2026-04-24 05:23

Tell Me Why: Designing an Explainable LLM-based Dialogue System for Student Problem Behavior Diagnosis

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 expl…