One-to-one tutoring is one of the most efficient methods of teaching. Following the rise in popularity of Large Language Models (LLMs), there have been efforts to use them to create conversational tutoring systems, which can make the benefits of one-to-one tutoring accessible to everyone. However, current LLMs are primarily trained to be helpful assistants and thus 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 scenarios, they need to be steered towards using effective teaching strategies: a problem we introduce as Pedagogical Steering and believe to be crucial for the efficient use of LLMs as tutors. We address this problem by formalizing a concept of tutoring strategy, and introducing StratL, an algorithm to model a strategy and use prompting to steer the LLM to follow this strategy. 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. We quantitatively show that StratL succeeds in steering the LLM to follow a Productive Failure tutoring strategy. We also thoroughly investigate the existence of spillover effects on desirable properties of the LLM, like its ability to generate human-like answers. Based on these results, we highlight the challenges in Pedagogical Steering and suggest opportunities for further improvements. We further encourage follow-up research by releasing a dataset of Productive Failure problems and the code of our prototype and algorithm.

翻译：一对一辅导是最高效的教学方法之一。随着大型语言模型（LLM）的普及，学界已尝试利用其构建对话式辅导系统，使一对一辅导的优势惠及大众。然而，当前LLM主要被训练为辅助工具，缺乏关键的教学能力。例如，它们常过早向学生揭示答案，且难以规划丰富的多轮教学互动。为将LLM应用于教学场景，需引导其采用有效的教学策略——这一问题我们称之为"教学引导"，并认为其对高效利用LLM作为辅导工具至关重要。我们通过形式化辅导策略概念，提出StratL算法来建模策略并利用提示工程引导LLM遵循该策略。作为案例研究，我们基于"生产性失败"（Productive Failure, PF）这一先进有效的学习设计理念，开发了面向高中数学的辅导原型。为在真实场景中验证方法，我们在新加坡对17名高中生开展实地研究。定量分析表明StratL成功引导LLM遵循生产性失败辅导策略。我们深入探究了该方法对LLM期望特性（如生成类人回答的能力）可能产生的溢出效应。基于研究结果，我们指出教学引导面临的挑战并提出改进方向。为促进后续研究，我们公开了生产性失败问题数据集及原型系统与算法的代码。