用算法让大模型按教学策略互动，提升辅导效果
Towards the Pedagogical Steering of Large Language Models for Tutoring: A Case Study with Modeling Productive Failure
- 设计提示优化算法StratL，让LLM按预设教学流程对话
- 17名新加坡中学生实测显示，模型能有效执行‘失败促学’策略
- 适合教育科技研究者与智能辅导系统开发者参考
一对一辅导是高效的教学方式。随着大语言模型（LLMs）的兴起，研究者尝试构建基于LLM的对话式辅导系统，以将个性化辅导推广至更广泛人群。然而，当前LLM主要训练为助手角色，缺乏关键的教学技能，如过早揭示答案、无法规划多轮互动。为此，本文提出“教学引导”（Pedagogical Steering）问题，并开发StratL算法，通过优化提示词，使模型遵循由转移图表示的多轮教学计划。作为案例，我们构建了一个针对高中数学的原型辅导系统，采用“失败促学”（Productive Failure, PF）这一高效学习设计。在新加坡开展的实地研究中，17名高中生参与测试，结果表明StratL成功引导模型执行PF教学策略。研究还发布了一个包含PF题目的数据集及代码，揭示了教学引导的挑战并提出改进方向。
原文摘要 · Abstract (English)
One-to-one tutoring is one of the most efficient methods of teaching. With the growing popularity of Large Language Models (LLMs), there have been efforts to create LLM based conversational tutors which can expand the benefits of one to one tutoring to everyone. However, current LLMs are trained primarily to be helpful assistants and lack crucial pedagogical skills. For example, they often quickly reveal the solution to the student and fail to plan for a richer multi turn pedagogical interaction. To use LLMs in pedagogical settings, they need to be steered to use effective teaching strategies: a problem we introduce as Pedagogical Steering. We develop StratL, an algorithm to optimize LLM prompts and steer it to follow a predefined multi-turn tutoring plan represented as a transition graph. As a case study, we create a prototype tutor for high school math following Productive Failure (PF), an advanced and effective learning design. To validate our approach in a real-world setting, we run a field study with 17 high school students in Singapore and show that StratL succeeds in steering the LLM to follow the PF tutoring strategy. Finally, we highlight challenges in Pedagogical Steering of LLMs and offer opportunities for further improvements by publishing a dataset of PF problems and our code.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。