训练基于大语言模型的辅导系统以提升对话中的学生学习效果
Training LLM-based Tutors to Improve Student Learning Outcomes in Dialogues
AI总结：
本研究针对现有AI辅导系统未以对话全程学生学习最大化为目标的问题，提出结合学生答对概率预测与教学评分、用直接偏好优化训练Llama 3.1 8B的方法，在保持教学质量的同时显著提升了学生答题正确率。
摘要：
生成式人工智能（AI）具备通过大语言模型（LLM）规模化推广个性化辅导的潜力。当前的AI辅导系统通过训练或提示LLM遵循有效教学原则来适配辅导任务，但并未经过在整个对话过程中最大化学生学习效果的训练，因此它们与学生的互动方式可能并非最优。\n我们针对这一局限提出了一种训练LLM生成辅导话语的方法，该方法在鼓励模型遵循良好教学规范的同时，最大化学生答对问题的概率。具体而言，我们生成一组候选辅导话语，并通过两个维度打分：（1）基于LLM的学生模型，用于预测学生给出正确回答的概率；（2）由GPT-4o评估的教学评分标准。随后我们利用生成的数据，通过直接偏好优化（DPO）训练开源LLM Llama 3.1 8B。\n实验表明，我们的模型生成的辅导话语在保持GPT-4o级别的教学质量的同时，能显著提升学生给出正确回答的概率。我们还开展了定性分析与人工评估，证明该模型能生成高质量的辅导话语。
英文摘要：
Generative artificial intelligence (AI) has the potential to scale up personalized tutoring through large language models (LLMs). Recent AI tutors are adapted for the tutoring task by training or prompting LLMs to follow effective pedagogical principles, though they are not trained to maximize student learning throughout the course of a dialogue. Therefore, they may engage with students in a suboptimal way. We address this limitation by introducing an approach to train LLMs to generate tutor utterances that maximize the likelihood of student correctness, while still encouraging the model to follow good pedagogical practice. Specifically, we generate a set of candidate tutor utterances and score them using (1) an LLM-based student model to predict the chance of correct student responses and (2) a pedagogical rubric evaluated by GPT-4o. We then use the resulting data to train an open-source LLM, Llama 3.1 8B, using direct preference optimization. We show that tutor utterances generated by our model lead to significantly higher chances of correct student responses while maintaining the pedagogical quality of GPT-4o. We also conduct qualitative analyses and a human evaluation to demonstrate that our model generates high quality tutor utterances.
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。
