ORIGINAL RESEARCH article
Front. Sports Act. Living
Sec. Physical Education and Pedagogy
Augmentation or substitution: defining role of large language model in physical education
Provisionally accepted
- Chongqing University of Posts and Telecommunications, Chongqing, China
Select one of your emails
You have multiple emails registered with Frontiers:
Notify me on publication
Please enter your email address:
If you already have an account, please login
You don't have a Frontiers account ? You can register here
Large language model has gained widespread use in the field of education due to the swift advancement of artificial intelligence technology. As the capabilities of large language models are used in areas such as healthcare planning and question answering, this highlights their potential for personalised teaching in physical education. However, there are also studies that have raised concerns about the risks associated with the use of large language models. This study explores the role of large language model in physical education and assess its applicability as an aid or alternative. Using a questionnaire, this study compares the performance of three different generative approaches in terms of feasibility, practicality, safety, adaptability, and content quality. We also assessed large language model for response accuracy, safety, clarity, adaptability, guidance, response acceptability, and its potential to enhance teacher response efficiency in the physical education setting. The results showed that lesson plans generated by physical education teachers in collaboration with large language model were superior in all aspects to those generated directly by large language model or after feeding resources. In addition, the overall performance of large language model responses in the physical education setting was superior. The paper summarises the strengths and limitations of large language model in physical education and concludes that large language model is more suitable as an assistive tool to help physical education teachers optimise the effectiveness of their teaching rather than a complete replacement of the role of a human teacher.
Keywords: Large Language Model, Physical Education, artificial intelligence, Assistive tools, Sustainability teaching
Received: 13 Jul 2025; Accepted: 24 Oct 2025.
Copyright: © 2025 Yang, Huang and Li. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence: Xu Li, lixu@cqupt.edu.cn
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.