提升K-12教育中AI辅导质量的方法
Methodologies for Improving the Quality of AI Tutoring in K-12 Education
浏览论文内容
中文总结 AI 辅助
本文针对K-12教育中AI辅导质量提升问题,以Khanmigo为研究对象,介绍了相关衡量指标与实验,阐述了模型、提示工程等方面对指标产生积极影响的改动。
中文摘要 AI 辅助
如今许多AI辅导工具都利用了大语言模型(LLMs)。鉴于LLMs是不透明的黑箱,对每一项改动的影响进行稳健评估和实时实验至关重要。我们于2023年推出了Khanmigo(可汗学院的AI辅导工具),率先将AI技术应用于K-12教育辅导。本文介绍了我们用于衡量AI辅导质量和学生参与度的指标,以及开展的各项实验,重点说明了对指标产生积极影响的改动,涉及模型、提示工程、个性化设置和智能体等方面。
英文摘要
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.
发表机构
- Khan Academy(可汗学院)
机构由 AI 辅助整理,请以论文原文为准。