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.

翻译：近年来，大语言模型（LLMs）的发展显示出其作为教育导师的潜力。然而，不同的教学策略适用于不同性格的学生，策略与性格的不匹配可能对学生的学习效果产生负面影响。尽管如此，当前基于大语言模型的辅导系统并未考虑学生的性格特质。为解决此问题，我们首先基于教育学文献构建了一个将教学方法与性格特征相关联的分类体系。通过模拟师生对话，我们利用该框架使大语言模型导师能够根据模拟学生的性格调整其教学策略。我们邀请人类教师对该情境进行评估，发现他们一致认为我们的方法优于两种基线模型。我们的方法还增加了角色扮演等使用频率较低但影响显著的高阶策略的应用，这些策略获得了人类与大语言模型标注者的显著青睐。我们的研究结果为在教育应用中开发更具个性化且更有效的大语言模型使用方式奠定了基础。