利用机器去学习和再学习在大语言模型中模拟新手学生
Simulating Novice Students Using Machine Unlearning and Relearning in Large Language Models
AI总结：
本文提出基于机器去学习的知识级模拟方法，通过转换知识丰富的LLM为新手级AI学生，评估其通过教学对话重新学习知识的能力，揭示了学生行为随时间的变化轨迹。
摘要：
学生模拟可以支持教学式学习教学法，其中人类学生（作为导师）教授AI模拟的新手学生（作为被教导者）。近期研究常依赖大语言模型（LLMs）的提示工程来模拟新手学生行为，但难以保持AI模拟学生在稳定的新手知识水平。关键原因在于许多LLMs被训练为广泛具备能力，因此即使被提示“扮演新手”，LLMs在学习-教学交互过程中仍可能生成专家级解释。因此，我们提出基于机器去学习的知识级模拟方法。我们使用包含多个选择题的Python编程概念数据集研究此方法。我们应用机器去学习将知识丰富的LLM转换为新手级AI学生（即可教导代理），然后评估该可教导代理是否能通过学习-教学对话交互重新学习目标知识组件。最后，我们分析对话日志，以描述代理行为随时间的变化，包括其提问、错误模式和对指令的响应。结果表明：（1）去学习产生比仅提示基线更像新手的模拟学生代理；（2）代理在结构化暴露下可恢复部分被去学习的知识；（3）对话分析揭示了可识别的概念变化轨迹和教学动作，预测学习恢复。
英文摘要：
Student simulation can support learning-by-teaching pedagogy where human students (as tutors) teach AI-simulated novice students (as tutees). Recent research often relies on prompt engineering with large language models (LLMs) to simulate novice student behaviour, but it is difficult to keep the AI-simulated student at a stable novice knowledge level. A key reason is that many LLMs are trained to be broadly capable, so even when prompted to "act like a novice," the LLMs can still produce expert-level explanations during the learning-by-teaching interaction process. As a result, the AI-simulated student may drift beyond the intended knowledge level, reducing the credibility of the simulation for studying learning-by-teaching processes. Thus, we propose a knowledge-level simulation approach based on machine unlearning. We investigate this approach using a dataset of multiple-choice questions on Python programming concepts. We apply machine unlearning to transform a knowledgeable LLM into a novice-level AI student (i.e., teachable agent), then evaluate whether the teachable agent can relearn targeted knowledge components through learning-by-teaching dialogue interactions. Finally, we analyse the dialogue logs to characterise how the agent's behaviour changes over time, including its question asking, error patterns, and responsiveness to instruction. The results show that (1) unlearning produces simulated student agents with more novice-like responses than prompt-only baselines, (2) the agents recover a measurable portion of the unlearned knowledge under structured exposure, and (3) dialogue analyses reveal identifiable trajectories of conceptual change and teaching moves that predict learning recovery.
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。
