面向即时自适应反馈：通过知识增强的大语言模型提升学生学习
Towards Just-in-Time Adaptive Feedback: Enhancing Student Learning via Knowledge-Grounded LLM
AI总结：
提出一个框架，利用领域专家知识增强大语言模型，在真实教学场景中提供即时自适应反馈，并在大规模大学课程中提升学生成绩超过80%。
摘要：
教育干预是提升学生学习的有效工具。虽然大语言模型（LLMs）允许大规模生成自适应反馈，但当前研究缺乏在真实教学环境中提供即时（JiT）反馈的明确方法。在本文中，我们提出了一个框架，通过将LLMs与领域专家知识相结合来提供自适应反馈。我们的方法收集学生的书面推理逻辑（策略文章），基于推理内容分析潜在错误类型，并提供非侵入性反馈，旨在澄清缺失或错误的概念。我们在一个大规模大学课程（N > 1000）中部署了该框架，与以往学期相比，学生成绩提升了超过80%。最后，我们通过分析学习轨迹验证了该框架的教学实用性；我们展示了与LLM的迭代对话如何促进从错误概念向正确理解的转变。
英文摘要：
Educational interventions are effective tools for enhancing student learning. While Large Language Models (LLMs) allow for generating adaptive feedback at scale, current studies lack clear methodologies for providing Just-in-Time (JiT) feedback in authentic instructional settings. In this paper, we present a framework that provides adaptive feedback by grounding LLMs with domain-specific expert knowledge. Our approach collects written reasoning logic (strategy essays) from students, analyzes potential error types based on the content of that reasoning, and delivers non-intrusive feedback designed to clarify missing or incorrect concepts. We deploy this framework in a large-scale university course (N > 1000), where it improved student performance by over 80% compared to previous semesters. Lastly, we validate the framework's pedagogical utility by analyzing the learning trajectories; we demonstrate how iterative conversations with LLM facilitate shifting one's misconception to correct understanding.
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。
