让AI通过互动教学自我学习，快速生成可靠智能辅导系统。
AI2T: Building Trustable AI Tutors by Interactively Teaching a Self-Aware Learning Agent
- 作者用少量解题步骤和评分指导AI，使其自动生成解题规则。
- 仅20-30分钟训练即可准确判断自身解题把握度，优于现有方法。
- 适合需要高效、可信智能辅导系统开发的教育科技研究者。
AI2T是一种可交互教学的AI，用于构建智能辅导系统（ITS）。作者通过提供少量逐步解题示范并评分，指导AI2T学习。仅需20-30分钟互动训练，AI2T即可推导出稳健的逐步解题追踪规则（即模型追踪）。在学习过程中，它能利用STAND——一种自知前提学习算法，精准估计其在未见问题步骤上的正确性把握度，表现优于XGBoost等前沿方法。用户研究表明，作者可借助STAND的置信度启发式判断训练是否充分，从而生成完整正确的模型追踪程序。相比易产生幻觉的LLM及以往教学式编写方法，AI2T生成的程序更可靠。凭借其对层级规则的自知式归纳，AI2T为复杂智能辅导系统提供了高效率、可信赖的开发路径，常规需200-300小时编程才能实现一小时教学内容。
原文摘要 · Abstract (English)
AI2T is an interactively teachable AI for authoring intelligent tutoring systems (ITSs). Authors tutor AI2T by providing a few step-by-step solutions and then grading AI2T's own problem-solving attempts. From just 20-30 minutes of interactive training, AI2T can induce robust rules for step-by-step solution tracking (i.e., model-tracing). As AI2T learns it can accurately estimate its certainty of performing correctly on unseen problem steps using STAND: a self-aware precondition learning algorithm that outperforms state-of-the-art methods like XGBoost. Our user study shows that authors can use STAND's certainty heuristic to estimate when AI2T has been trained on enough diverse problems to induce correct and complete model-tracing programs. AI2T-induced programs are more reliable than hallucination-prone LLMs and prior authoring-by-tutoring approaches. With its self-aware induction of hierarchical rules, AI2T offers a path toward trustable data-efficient authoring-by-tutoring for complex ITSs that normally require as many as 200-300 hours of programming per hour of instruction.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。