通过强化学习提升自动生成反馈的有效性
Improving the Validity of Automatically Generated Feedback via Reinforcement Learning
AI总结：
针对智能辅导中LLM生成数学反馈的正确性与教学有效性不足问题，提出数学反馈评估 rubric 及基于RL、DPO的反馈生成框架，显著提升了Llama 2生成反馈的质量。
摘要：
在智能辅导系统和在线学习平台中，利用大语言模型（large language models, LLMs）自动生成反馈具备提升众多学生学习成效的潜力。但反馈生成与评估均存在挑战：尤其在数学这类学科中，反馈内容必须具备正确性，这要求模型理解题目、解法以及学生的错误所在；反馈还需具备教学层面的有效性，以体现高效的辅导策略，例如解释可能的错误认知、鼓励学生等其他理想特性。\n本研究同时解决自动生成与评估反馈的两大问题，兼顾正确性与契合度。首先，我们提出一套用于评估数学反馈的评分标准，并证明GPT-4能够有效利用该标准对人工撰写及LLM生成的反馈进行标注。其次，我们提出一种反馈生成框架，采用强化学习（reinforcement learning, RL）同时优化正确性与契合度。具体而言，我们利用GPT-4的标注在增强数据集上构建反馈配对的偏好数据，以通过直接偏好优化（direct preference optimization, DPO）进行训练。实验表明，我们的方法显著提升了开源LLM——Llama 2生成反馈的正确性与契合度，我们还通过案例研究对生成与评估系统进行了定性分析，并列出了若干未来研究方向。
英文摘要：
Automatically generating feedback via large language models (LLMs) in intelligent tutoring systems and online learning platforms has the potential to improve the learning outcomes of many students. However, both feedback generation and evaluation are challenging: feedback content has to be valid especially in subjects like math, which requires models to understand the problem, the solution, and where the student's error lies. Feedback also has to be pedagogically valid to reflect effective tutoring strategies, such as explaining possible misconceptions and encouraging the student, among other desirable features. In this work, we address both problems of automatically generating and evaluating feedback while considering both correctness and alignment. First, we propose a rubric for evaluating math feedback and show that GPT-4 is able to effectively use it to annotate human-written and LLM-generated feedback. Second, we propose a framework for feedback generation that optimizes both correctness and alignment using reinforcement learning (RL). Specifically, we use GPT-4's annotations to create preferences over feedback pairs in an augmented dataset for training via direct preference optimization (DPO). We show that our methods significantly increase the correctness and alignment of generated feedback with Llama 2, an open-source LLM, qualitatively analyze our generation and evaluation systems using case studies, and outline several areas for future work.
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。
