用自适应提示提升AI家教的课堂互动效率
Learning to Prompt: Improving Student Engagement with Adaptive LLM-based High-School Tutoring
- 根据14个教学特征动态选择合适提示
- 减少约3轮对话，转化率最高达28.1%
- 适合需要个性化辅导的中学教育场景
大型语言模型可实现个性化教育，但现有静态提示系统难以适配不同学科。本研究基于14项教学特征（如导师支架、学生理解度）从原始对话中提取信息，构建主题感知提示路由模型。先在模拟环境中训练模型，再部署至真实高中生群体进行在线适应。模拟基准测试显示，该路由模型优于两种静态基线（0.694 vs. 0.647 和 0.64，p<0.001）。A/B测试（N=656次对话，来自359名学生）表明，模型能从分析型策略转为支架型策略。自适应提示机制提升了教学效率，保持教学质量的同时减少约3轮交互（p=0.007）。贪心路由与基线转化率相近（19.1% vs. 19.6%），而随机采样策略的转化率更高（28.1%）。
原文摘要 · Abstract (English)
LLMs can personalize education, although current static-prompt tutoring systems struggle to adapt to diverse academic disciplines. We develop and test a system with subject-aware prompting, based on 14 pedagogical features (e.g., tutor scaffolding, student understanding) extracted from raw transcripts. We first train a prompt routing model in a simulation environment, and then deploy it for online adaptation with actual high-school students. The simulation benchmark shows the router outperforming two static baselines ($0.694$ vs. $0.647$ and $0.64$, $p<0.001$). A/B testing ($N=656$ conversations from 359 students) shows sim-to-real transfer where the model switches from analytical to scaffolding learning strategies. Our adaptive prompt selection mechanism improves instructional efficiency, maintains pedagogical quality and reduces interactions by around 3 turns ($p=0.007$). While a greedy router achieves a comparable exercise conversion rate with the baseline ($19.1\%$ vs. $19.6\%$), a stochastic router that samples strategies leads to a higher conversion rate ($28.1\%$).
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。