Application of large language models in oral health education: a review of the literature.

Background: The recent emergence of artificial intelligence and large language models (LLMs) has caused educators to be cautious about applying these technologies in education. This narrative review explores the current literature to identify the existing applications of LLMs in dental and dental hygiene education. Methods: An extensive literature search in PubMed, CINAHL Plus, and Education Research Complete was conducted. The search string was (((Large language model) OR (Chatbot)) OR (ChatGPT)) AND (Dental education)). Primary research articles published in English and relevant to the research questions were included. Articles were screened by title and then by full-text review. Data were extracted from the eligible studies. Results: After 2 rounds of screening, 28 articles were selected for review. The LLMs used in the studies were ChatGPT versions 3, 3.5, 4, 4o, 4V; Bing Chat; Bard; Gemini; Copilot; Llama 2; Claude3-Opus and custom chatbots developed by the authors. Data analysis revealed 2 major themes in the research: 1) the performance of LLMs on standardized exams and 2) LLMs as teaching tools. Discussion: Many studies reported that LLMs can pass high-stakes dental exams, raising concerns about current assessment methods. However, findings that LLMs perform poorly in critically appraising literature and interpretation-type questions are insightful for educators when designing new assignments and assessment plans for dental and dental hygiene students. Conclusion: LLMs are rapidly developing as artificial intelligence advances. Repeated studies are needed to assess the impact of LLMs on teaching, learning, and assessment experiences.