Application of large language models in oral health education: a review of the literature.
Bibliographic record
Abstract
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.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.008 | 0.024 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.002 |
| Bibliometrics | 0.008 | 0.007 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.003 | 0.004 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.004 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".