Large Language Models for Education: A Survey

TL;DR

This survey examines the elevation of education through large language models (LLMs) by analyzing current technologies, educational contexts, and deployment processes. It synthesizes a framework of core technologies, implementation pathways, and practical benefits, while detailing risks such as hallucinations, privacy, equity, and governance. The authors propose a staged integration strategy with fusion approaches, industry examples, and math-specific applications to realize personalized, scalable, and interdisciplinary learning. Emphasizing human-centric design, evaluation benchmarks, and policy considerations, the paper outlines what is needed to responsibly harness LLMEdu and highlights directions toward multimodal capabilities and tool-assisted reasoning.

Abstract

Artificial intelligence (AI) has a profound impact on traditional education. In recent years, large language models (LLMs) have been increasingly used in various applications such as natural language processing, computer vision, speech recognition, and autonomous driving. LLMs have also been applied in many fields, including recommendation, finance, government, education, legal affairs, and finance. As powerful auxiliary tools, LLMs incorporate various technologies such as deep learning, pre-training, fine-tuning, and reinforcement learning. The use of LLMs for smart education (LLMEdu) has been a significant strategic direction for countries worldwide. While LLMs have shown great promise in improving teaching quality, changing education models, and modifying teacher roles, the technologies are still facing several challenges. In this paper, we conduct a systematic review of LLMEdu, focusing on current technologies, challenges, and future developments. We first summarize the current state of LLMEdu and then introduce the characteristics of LLMs and education, as well as the benefits of integrating LLMs into education. We also review the process of integrating LLMs into the education industry, as well as the introduction of related technologies. Finally, we discuss the challenges and problems faced by LLMEdu, as well as prospects for future optimization of LLMEdu.

Figures (6)

• Figure 1: Framework of LLMs.
• Figure 2: The characteristics of LLMEdu.
• Figure 3: Reasons for integrating LLM into education.
• Figure 4: Key technologies of the LLMs
• Figure 5: Examples of LLMEdu.