迈向情境中教学：根据学生的错误概念调整示例
Toward In-Context Teaching: Adapting Examples to Students' Misconceptions
AI总结：
本文提出 AdapT 评估套件与自适应教学概率模型 AToM，通过模拟学生和人类实验验证其能依据学生知识状态选择示例，效果优于随机选择及多种基线方法。
摘要：
当教师为学生提供供其学习的示例时，这些示例必须具有信息量，使学生能够从当前状态向目标概念或技能进步。因此，优秀教师必须同时推断学生已经知道什么，并根据学生不断变化的知识状态调整教学。人们越来越关注将计算模型，尤其是大型语言模型，用作教学工具。作为学生，语言模型尤其展现出在给定少量示例的情况下适应新任务的卓越能力。但这些模型作为教师，能够在多大程度上有效适应不同类型的学生？为研究这一问题，我们引入了一套模型与评估方法，称为 AdapT。AdapT 包含两个组成部分：（1）一组模拟贝叶斯学生模型，可用于评估自动化教学方法；（2）一个面向人类学生的评估平台，用于刻画这些方法在真实世界中的有效性。我们还提出了（3）AToM，这是一种用于自适应教学的新型概率模型，可联合推断学生过去的信念，并优化未来信念的正确性。在跨越三个学习领域（分数算术、英语形态学、函数学习）的模拟学生评估中，AToM 系统性地优于基于 LLM 的教学模型和标准贝叶斯教学模型。在人类实验中，AToM 和 LLM 均优于非自适应的随机示例选择。我们的结果既凸显了自适应教学任务的难度，也展示了学习型自适应模型解决该任务的潜力。
英文摘要：
When a teacher provides examples for a student to study, these examples must be informative, enabling a student to progress from their current state toward a target concept or skill. Good teachers must therefore simultaneously infer what students already know and adapt their teaching to students' changing state of knowledge. There is increasing interest in using computational models, particularly large language models, as pedagogical tools. As students, language models in particular have shown a remarkable ability to adapt to new tasks given small numbers of examples. But how effectively can these models adapt as teachers to students of different types? To study this question, we introduce a suite of models and evaluation methods we call AdapT. AdapT has two components: (1) a collection of simulated Bayesian student models that can be used for evaluation of automated teaching methods; (2) a platform for evaluation with human students, to characterize the real-world effectiveness of these methods. We additionally introduce (3) AToM, a new probabilistic model for adaptive teaching that jointly infers students' past beliefs and optimizes for the correctness of future beliefs. In evaluations of simulated students across three learning domains (fraction arithmetic, English morphology, function learning), AToM systematically outperforms LLM-based and standard Bayesian teaching models. In human experiments, both AToM and LLMs outperform non-adaptive random example selection. Our results highlight both the difficulty of the adaptive teaching task and the potential of learned adaptive models for solving it.
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。
