Large Language Models for Education: A survey and outlook

作者：Shen Wang, T. Xu, Hang Li, Chaoli Zhang, Joleen Liang, Jiliang Tang, Philip S. Yu, Qingsong Wen · 发表于：IEEE Signal Processing Magazine · 年份：2025 · DOI：10.1109/msp.2025.3594309 · 被引用次数：33 · 研究领域：Computational and Text Analysis Methods、Text Readability and Simplification、Second Language Acquisition and Learning

The advent of large language models (LLMs) has ushered in a new era of possibilities in the realm of education. This survey article summarizes recent progress in the application of LLMs in educational settings from multiple perspectives, including student and teacher assistance, adaptive learning, and commercial tools. Additionally, it systematically reviews technological advancements in each area, compiles related datasets and benchmarks, and identifies the risks and challenges associated with deploying LLMs in education. Furthermore, the article outlines future research opportunities, highlighting promising directions. This article aims to provide a comprehensive technological overview for educators, researchers, and policy makers to harness the power of LLMs, revolutionize educational practices, and foster a more effective personalized learning environment.