This work investigates large language models (LLMs) as teachable agents for learning by teaching (LBT). LBT with teachable agents helps learners identify knowledge gaps and discover new knowledge. However, teachable agents require expensive programming of subject-specific knowledge. While LLMs as teachable agents can reduce the cost, LLMs' expansive knowledge as tutees discourages learners from teaching. We propose a prompting pipeline that restrains LLMs' knowledge and makes them initiate "why" and "how" questions for effective knowledge-building. We combined these techniques into TeachYou, an LBT environment for algorithm learning, and AlgoBo, an LLM-based tutee chatbot that can simulate misconceptions and unawareness prescribed in its knowledge state. Our technical evaluation confirmed that our prompting pipeline can effectively configure AlgoBo's problem-solving performance. Through a between-subject study with 40 algorithm novices, we also observed that AlgoBo's questions led to knowledge-dense conversations (effect size=0.71). Lastly, we discuss design implications, cost-efficiency, and personalization of LLM-based teachable agents.

翻译：本研究探讨了将大语言模型（LLMs）作为可教学代理，用于"通过教学来学习"（LBT）的方法。采用可教学代理的LBT能帮助学习者识别知识盲点并发现新知识。然而，可教学代理需要针对特定学科知识进行昂贵的编程开发。虽然将LLMs作为可教学代理可以降低这种成本，但作为学习者的LLMs所拥有的广泛知识反而会抑制学习者的教学意愿。我们提出了一种提示流水线，通过限制LLMs的知识范围，并使其能主动提出"为什么"和"如何"类问题来促进有效知识构建。我们将这些技术整合到用于算法学习的LBT环境TeachYou中，并开发了基于LLM的辅导聊天机器人AlgoBo，它能模拟其知识状态中预设的误解和认知缺失。技术评估证实，我们的提示流水线能有效配置AlgoBo的问题解决能力。通过对40名算法初学者的组间实验，我们观察到AlgoBo提出的问题能引发知识密集型对话（效应量=0.71）。最后，我们讨论了基于LLM的可教学代理的设计启示、成本效益及个性化方案。