Large language models in education: a systematic review of empirical applications, benefits, and challenges

The rapid advancement of Large Language Models (LLMs), particularly following the release of ChatGPT in November 2022, has significantly transformed educational methodologies. This systematic review aims to synthesize empirical studies published between November 2022 and March 2025, examining the implementation and effectiveness of LLMs in educational settings. 88 empirical studies identified key applications, benefits, and challenges associated with LLM integration in education. Our findings reveal that LLMs are utilized across various educational contexts in six primary applications, with Intelligent Tutoring Systems being particularly prominent. The benefits include improved academic performance, increased student engagement, enhanced accessibility, optimized resource utilization, and strengthened cognitive and skill development. However, challenges such as student over-reliance on AI, technical reliability issues, assessment fairness, and privacy concerns were identified. This review provides educators, researchers, and policymakers with evidence-based insights and practical guidance for effective LLM integration, contributing to the ongoing transformation of teaching and learning in the era of Generative Artificial Intelligence (GenAI) technology.