让AI导师根据学生性格调整教学策略，提升学习效果
PATS: Personality-Aware Teaching Strategies with Large Language Model Tutors
- 基于教育文献构建教学法与性格的匹配框架
- 模拟对话中动态调整策略，显著提升高影响力教学法使用率
- 适合个性化教育系统开发者与教育AI研究者
大型语言模型（LLM）在教育辅导中展现出巨大潜力，但不同教学策略对不同性格的学生效果各异，匹配不当反而适得其反。当前的LLM辅导系统未考虑学生性格特征。为此，我们基于教育学文献构建了教学方法与性格类型的对应关系体系，通过模拟师生对话，使LLM导师根据模拟学生性格动态调整教学策略。与人类教师对比评估显示，该方法在所有测试场景中均获得更高偏好。同时，该方法显著提高了角色扮演等少见但高影响力的策略使用频率，得到人类与LLM标注者的显著青睐。研究为实现更个性化、高效的教育型LLM应用提供了新路径。
原文摘要 · Abstract (English)
Recent advances in large language models (LLMs) demonstrate their potential as educational tutors. However, different tutoring strategies benefit different student personalities, and mismatches can be counterproductive to student outcomes. Despite this, current LLM tutoring systems do not take into account student personality traits. To address this problem, we first construct a taxonomy that links pedagogical methods to personality profiles, based on pedagogical literature. We simulate student-teacher conversations and use our framework to let the LLM tutor adjust its strategy to the simulated student personality. We evaluate the scenario with human teachers and find that they consistently prefer our approach over two baselines. Our method also increases the use of less common, high-impact strategies such as role-playing, which human and LLM annotators prefer significantly. Our findings pave the way for developing more personalized and effective LLM use in educational applications.
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。