MisEdu-RAG：一种面向初学者数学教师的误解意识双超图RAG
MisEdu-RAG: A Misconception-Aware Dual-Hypergraph RAG for Novice Math Teachers
AI总结：
针对初学者数学教师难以诊断和纠正学生错误的问题，提出基于双超图的RAG框架，通过组织教学知识和学生错误案例，提升响应质量。
摘要：
初学者数学教师常面临难以诊断和纠正的学生错误。误解尤其具有挑战性，因为教师必须解释错误所在并指导解决方法。尽管许多现有大语言模型（LLM）平台能帮助生成教学反馈，但这些LLM松散连接教学知识和学生错误，可能使指导对教师不够实用。为此，我们提出MisEdu-RAG，一种基于双超图的检索增强生成（RAG）框架，将教学知识作为概念超图，真实学生错误案例作为实例超图。给定查询时，MisEdu-RAG执行两阶段检索以从两个层次收集相关证据，并生成基于检索案例和教学原则的响应。我们在\textit{MisstepMath}数据集上进行评估，该数据集包含数学错误与教师解决方案的配对，作为跨主题和错误类型的误解意识检索和响应生成基准。在\textit{MisstepMath}上的评估结果表明，与基线模型相比，MisEdu-RAG将token-F1提高10.95%，响应质量提升达15.3%，在\textit{Diversity}和\textit{Empowerment}方面提升最大。为进一步验证其在实际应用中的适用性，我们通过221名教师的问卷调查和6名初学者的访谈进行了试点研究。研究结果表明，MisEdu-RAG为高需求误解场景提供诊断结果和具体的教学方法。总体而言，MisEdu-RAG在可扩展的教师培训和AI辅助的误解处理教学中展现出强大潜力。我们的代码可在GitHub上获取：https://github.com/GEMLab-HKU/MisEdu-RAG。
英文摘要：
Novice math teachers often encounter students' mistakes that are difficult to diagnose and remediate. Misconceptions are especially challenging because teachers must explain what went wrong and how to solve them. Although many existing large language model (LLM) platforms can assist in generating instructional feedback, these LLMs loosely connect pedagogical knowledge and student mistakes, which might make the guidance less actionable for teachers. To address this gap, we propose MisEdu-RAG, a dual-hypergraph-based retrieval-augmented generation (RAG) framework that organizes pedagogical knowledge as a concept hypergraph and real student mistake cases as an instance hypergraph. Given a query, MisEdu-RAG performs a two-stage retrieval to gather connected evidence from both layers and generates a response grounded in the retrieved cases and pedagogical principles. We evaluate on \textit{MisstepMath}, a dataset of math mistakes paired with teacher solutions, as a benchmark for misconception-aware retrieval and response generation across topics and error types. Evaluation results on \textit{MisstepMath} show that, compared with baseline models, MisEdu-RAG improves token-F1 by 10.95\% and yields up to 15.3\% higher five-dimension response quality, with the largest gains on \textit{Diversity} and \textit{Empowerment}. To verify its applicability in practical use, we further conduct a pilot study through a questionnaire survey of 221 teachers and interviews with 6 novices. The findings suggest that MisEdu-RAG provides diagnosis results and concrete teaching moves for high-demand misconception scenarios. Overall, MisEdu-RAG demonstrates strong potential for scalable teacher training and AI-assisted instruction for misconception handling. Our code is available on GitHub: https://github.com/GEMLab-HKU/MisEdu-RAG.
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。
