Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Large Language Models in Education: Vision and Opportunities

Wensheng Gan, Zhenlian Qi, Jiayang Wu, Jerry Chun-Wei Lin

TL;DR

This paper surveys the use of large language models in education (EduLLMs) and their role in smart education. It defines EduLLMs, discusses their relation to education and AI, and identifies key technologies, applications, and characteristics. It reviews training data, processes, integration with educational tech, and highlights challenges such as privacy, bias, interpretability, and equity. It provides future directions and practical guidance for educators, researchers, and policymakers.

Abstract

With the rapid development of artificial intelligence technology, large language models (LLMs) have become a hot research topic. Education plays an important role in human social development and progress. Traditional education faces challenges such as individual student differences, insufficient allocation of teaching resources, and assessment of teaching effectiveness. Therefore, the applications of LLMs in the field of digital/smart education have broad prospects. The research on educational large models (EduLLMs) is constantly evolving, providing new methods and approaches to achieve personalized learning, intelligent tutoring, and educational assessment goals, thereby improving the quality of education and the learning experience. This article aims to investigate and summarize the application of LLMs in smart education. It first introduces the research background and motivation of LLMs and explains the essence of LLMs. It then discusses the relationship between digital education and EduLLMs and summarizes the current research status of educational large models. The main contributions are the systematic summary and vision of the research background, motivation, and application of large models for education (LLM4Edu). By reviewing existing research, this article provides guidance and insights for educators, researchers, and policy-makers to gain a deep understanding of the potential and challenges of LLM4Edu. It further provides guidance for further advancing the development and application of LLM4Edu, while still facing technical, ethical, and practical challenges requiring further research and exploration.

Large Language Models in Education: Vision and Opportunities

TL;DR

This paper surveys the use of large language models in education (EduLLMs) and their role in smart education. It defines EduLLMs, discusses their relation to education and AI, and identifies key technologies, applications, and characteristics. It reviews training data, processes, integration with educational tech, and highlights challenges such as privacy, bias, interpretability, and equity. It provides future directions and practical guidance for educators, researchers, and policymakers.

Abstract

With the rapid development of artificial intelligence technology, large language models (LLMs) have become a hot research topic. Education plays an important role in human social development and progress. Traditional education faces challenges such as individual student differences, insufficient allocation of teaching resources, and assessment of teaching effectiveness. Therefore, the applications of LLMs in the field of digital/smart education have broad prospects. The research on educational large models (EduLLMs) is constantly evolving, providing new methods and approaches to achieve personalized learning, intelligent tutoring, and educational assessment goals, thereby improving the quality of education and the learning experience. This article aims to investigate and summarize the application of LLMs in smart education. It first introduces the research background and motivation of LLMs and explains the essence of LLMs. It then discusses the relationship between digital education and EduLLMs and summarizes the current research status of educational large models. The main contributions are the systematic summary and vision of the research background, motivation, and application of large models for education (LLM4Edu). By reviewing existing research, this article provides guidance and insights for educators, researchers, and policy-makers to gain a deep understanding of the potential and challenges of LLM4Edu. It further provides guidance for further advancing the development and application of LLM4Edu, while still facing technical, ethical, and practical challenges requiring further research and exploration.
Paper Structure (18 sections, 2 figures, 1 table)

This paper contains 18 sections, 2 figures, 1 table.

Table of Contents

  1. Introduction
  2. Education and LLMs
  3. Background of Education
  4. Background of LLMs
  5. Smart Education
  6. LLMs for Education
  7. Key Technologies for EduLLMs
  8. LLM-empowered Education
  9. Applications of Education under LLMs
  10. Characteristics of Education under LLMs
  11. Key Points in LLMsEdu
  12. Training Data and Preprocessing
  13. Training Process
  14. Integration with Educational Technologies
  15. Challenges and Future Directions
  16. ...and 3 more sections

Figures (2)

  • Figure 1: Architecture of LLMs for education (LLM4Edu).
  • Figure 2: The characteristics of education under LLMs.