Khanmigo用实验方法提升AI助教在中小学的辅导质量。
Methodologies for Improving the Quality of AI Tutoring in K-12 Education
- 通过实测评估模型、提示词与个性化策略的效果
- 优化后学生参与度与学习效果显著提升
- 适合教育科技研究者与AI教学实践者参考
当前许多AI助教采用大语言模型（LLMs）技术。由于LLMs具有黑箱特性，对每一项改动进行可靠评估与实时实验至关重要。我们于2023年推出Khanmigo（Khan Academy），开创了K-12教育中的AI辅导实践。本文介绍用于衡量AI辅导质量与学生参与度的指标体系，以及一系列实施的实验。重点展示了推动指标改善的关键改进，包括模型选型、提示工程、个性化适配和智能代理设计。
原文摘要 · Abstract (English)
Many AI tutors leverage large language models (LLMs) today. Given that LLMs are opaque black boxes, robust evaluation and live experimentation to measure the impact of every change are essential. We pioneered AI-powered tutoring for K-12 with the launch of Khanmigo (Khan Academy, 2023). We describe the metrics we use to measure AI tutoring quality and student engagement as well as various experiments we have run. We highlight the changes that have moved our metrics, including models, prompting, personalization and agents.
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。