面向辅导场景的大语言模型教学引导：以“有效失败”建模为例的案例研究
Towards the Pedagogical Steering of Large Language Models for Tutoring: A Case Study with Modeling Productive Failure
AI总结：
针对大语言模型缺乏教学技能的问题，提出教学引导概念与StratL算法，以“有效失败”学习设计打造高中数学辅导原型，经17名新加坡高中生实地研究验证有效，同时发布数据集与代码供后续研究。
摘要：
一对一辅导是最高效的教学方法之一。随着大语言模型（LLM）的日益普及，已有研究致力于打造基于LLM的对话式辅导工具，以期将一对一辅导的益处惠及所有人。然而，当前的LLM主要被训练为有用的助手，缺乏关键的教学技能。例如，它们往往会很快向学生透露答案，且无法规划更丰富的多轮教学互动。要在教学场景中使用LLM，需要引导它们运用有效的教学策略——我们将这一问题定义为“教学引导（Pedagogical Steering）”。我们开发了StratL算法，用于优化LLM的提示词，引导其遵循以转移图表示的预定义多轮辅导计划。作为案例研究，我们遵循“有效失败（Productive Failure，PF）”这一先进且有效的学习设计，打造了一个高中数学辅导原型。为在真实场景中验证我们的方法，我们对新加坡的17名高中生开展了实地研究，结果表明StratL成功引导LLM遵循了PF辅导策略。最后，我们指出了LLM教学引导面临的挑战，并通过发布PF问题数据集和我们的代码，为后续改进提供了研究基础。
英文摘要：
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.
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。
