A Scoping Review of Large Language Models in Dental Education: Applications, Challenges, and Prospects

With the rapid development of large language models (LLMs), their potential in dental clinical healthcare and education has become increasingly evident. However, the application of this emerging technology within dental education has not yet been systematically reviewed. This scoping review aims to summarize current applications, identify challenges encountered in the implementation process, and outline future prospects.

A comprehensive literature search was conducted in the PubMed, Web of Science, and Embase databases to identify studies related to LLMs and dental education. Relevant studies were screened, selected, and subjected to data extraction to collate information pertinent to the research questions.

A total of 37 studies were included. LLMs have been applied across seven distinct domains in dental education, notably in dental examinations (n = 24), educational information resources (n = 5), and assessment of students' assignments (n = 3). These applications have introduced several challenges, including technical issues (ie, inaccurate information, inability in image analysis, inaccessibility, and high cost) and application aspects (ie, ethical issues, absence of usage guidelines, potential harm to students' knowledge and skills, and cautious attitudes towards LLMs). Addressing these challenges requires coordinated efforts from students, educators, curriculum administrators, and technical developers.

The application of LLMs in dental education remains in its early stage. Future research should focus on expanding the range of applications and establishing standardized, ethically satisfying, and technically sound guidelines for integrating LLMs into dental education.