Learning in Context: Personalizing Educational Content with Large Language Models to Enhance Student Learning

2025-09-18

AI Summary

Standardized educational content often disregards students’ individual academic backgrounds and interests, resulting in low engagement and weak perceived relevance. To address this, we propose PAGE—a context-aware framework that enables automated, personalized content adaptation grounded in students’ disciplinary backgrounds and personal interests within authentic classroom settings. PAGE leverages large language models to dynamically restructure course materials and integrates an intelligent tutoring system to generate and deliver tailored content with precision. In controlled experiments, the intervention group demonstrated statistically significant improvements in learning outcomes (p < 0.01), alongside markedly increased learning engagement, perceived content relevance, and trust in the system. Our core contribution is a deployable, empirically validated paradigm for context-sensitive educational personalization—providing both rigorous evidence and a scalable technical pathway for AI-enhanced pedagogy.

Technology Category

• Humans and AI: Game Design — Procedural Content Generation & Storytelling
• Cognitive Modeling & Cognitive Systems: Adaptive Behavior
• Machine Learning: Learning Preferences or Rankings

Application Category

• User Modeling, Personalization and Recommendation: Personalized content ranking and presentation
• Search and Retrieval-Augmented AI: Personalized, context-aware and across-device search
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Standardized, one-size-fits-all educational content often fails to connect with students' individual backgrounds and interests, leading to disengagement and a perceived lack of relevance. To address this challenge, we introduce PAGE, a novel framework that leverages large language models (LLMs) to automatically personalize educational materials by adapting them to each student's unique context, such as their major and personal interests. To validate our approach, we deployed PAGE in a semester-long intelligent tutoring system and conducted a user study to evaluate its impact in an authentic educational setting. Our findings show that students who received personalized content demonstrated significantly improved learning outcomes and reported higher levels of engagement, perceived relevance, and trust compared to those who used standardized materials. This work demonstrates the practical value of LLM-powered personalization and offers key design implications for creating more effective, engaging, and trustworthy educational experiences.

Problem

• Personalizing educational content for individual student contexts
• Addressing disengagement from standardized one-size-fits-all materials
• Enhancing learning outcomes through LLM-powered adaptation

Innovation

• Personalizing educational content with LLMs
• Adapting materials to student context and interests
• Improving learning outcomes through AI personalization