从学生-辅导对话中诊断误解：生成、检索、重排序
Misconception Diagnosis From Student-Tutor Dialogue: Generate, Retrieve, Rerank
AI总结：
本文提出利用大语言模型从学生-辅导对话中检测误解的方法，通过生成、检索和重排序提升误解识别的准确性。
摘要：
及时准确地识别学生的误解对于提高学习成果和防止学生错误累积至关重要。然而，这项任务高度依赖教师的努力和直觉。在本工作中，我们提出了一种利用大语言模型（LLMs）从学生-辅导对话中检测误解的新方法。首先，我们使用微调的LLM生成可能的误解，然后通过嵌入相似性在这些生成中检索最有可能的候选者。这些候选者随后由另一个微调的LLM进行评估和重新排序，以提高误解的相关性。实证上，我们在一个教育辅导平台的实对话上评估我们的系统。我们考虑了多个基础LLM模型，包括LLaMA、Qwen和Claude，在零样本和微调设置下。我们发现，我们的方法在基线模型上提高了预测性能，且微调可以提高生成误解的质量，并且可以超越更大的闭源模型。最后，我们进行了消融研究，以验证我们的生成和重排序步骤对误解生成质量的重要性。
英文摘要：
Timely and accurate identification of student misconceptions is key to improving learning outcomes and pre-empting the compounding of student errors. However, this task is highly dependent on the effort and intuition of the teacher. In this work, we present a novel approach for detecting misconceptions from student-tutor dialogues using large language models (LLMs). First, we use a fine-tuned LLM to generate plausible misconceptions, and then retrieve the most promising candidates among these using embedding similarity with the input dialogue. These candidates are then assessed and re-ranked by another fine-tuned LLM to improve misconception relevance. Empirically, we evaluate our system on real dialogues from an educational tutoring platform. We consider multiple base LLM models including LLaMA, Qwen and Claude on zero-shot and fine-tuned settings. We find that our approach improves predictive performance over baseline models and that fine-tuning improves both generated misconception quality and can outperform larger closed-source models. Finally, we conduct ablation studies to both validate the importance of our generation and reranking steps on misconception generation quality.
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。
