PATS: Personality-Aware Teaching Strategies with Large Language Model Tutors

2026-01-13

AI Summary

This study addresses the limitation of existing large language model–based tutoring systems, which often overlook individual student differences, resulting in suboptimal instructional strategy adaptation. To bridge this gap, the work proposes a novel framework that integrates personality psychology with pedagogical theory, establishing a mapping between student personality traits and effective teaching strategies grounded in educational literature. Leveraging dialogue simulation and large language model–based reasoning, the system dynamically adapts its instructional approach in real time. Experimental results demonstrate a significant increase in both the frequency and quality of high-impact strategies—such as role-playing—compared to baseline methods. Human educator evaluations confirm the superiority of the proposed approach, thereby validating the effectiveness and practicality of automated, personality-aware adaptive instruction.

Technology Category

• Cognitive Modeling & Cognitive Systems: Adaptive Behavior
• Humans and AI: Learning Human Values and Preferences
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval

Application Category

• User Modeling, Personalization and Recommendation: Studies of user behavior, including longitudinal effects of personalized systems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

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.

Problem

• personality-aware tutoring
• large language models
• educational personalization
• teaching strategies
• student personality

Innovation

• personality-aware tutoring
• large language models
• adaptive teaching strategies
• pedagogical taxonomy
• personalized education