ChatGPT® and Knowledge of Brazilian Dental Ethics and Legislation
Open Access
- 1 January 2026
- journal article
- Published by FapUNIFESP (SciELO) in Pesquisa Brasileira em Odontopediatria e Clínica Integrada
- Vol. 26
Abstract
Objective: To investigate ChatGPT®’s knowledge of Brazilian dental ethics and legislation. Material and Methods: A cross-sectional study analyzed ChatGPT® 3.5’s responses to 281 dichotomous questions (“yes” or “no”) based on Federal Council of Dentistry (CFO) Resolution 118/2012 – Code of Dental Ethics (CEO) and Brazilian Law No. 5,081/1966 (L5081). The answer was “yes” in all cases, and when not provided, the question “What is the source of this information?” was asked. Answers were classified as “Correct,” “Partially correct,” and “Incorrect.” Errors were then reassessed with a reverse question: “What is described in Art. X of L5081?”. The same approach was applied to errors in the CEO, with classifications of “Correction,” “Same error,” and “New error.” Data were analyzed descriptively and using the Kruskal-Wallis test (α=5%). Results: Among answers, 134 (47.7%) were “Correct,” 127 (45.2%) were “Partially correct,” and 20 (7.1%) were “Incorrect.” Excluding the CEO’s initial and final provisions, Chapter XVII had the highest percentage of correct answers (n=7, 77.8%), while Chapter X had the highest rate of “Incorrect” answers (n=1, 25.0%). Of the 147 errors, 98.6% (n=145) generated a “New error.” No statistically significant difference was found among CEO chapters (p=0.058), but there was one between CEO and L5081 (p=0.005). Conclusion: ChatGPT®’s knowledge of Brazilian dental ethics and legislation may contain inaccuracies, and its use without source verification is not recommended.Keywords
Funding Information
- CAPES (001)
This publication has 26 references indexed in Scilit:
- A multimodal generative AI copilot for human pathologyNature, 2024
- Artificial intelligence in dental education: ChatGPT's performance on the periodontic in‐service examinationJournal of Periodontology, 2024
- GPT-3.5, GPT-4, or BARD? Evaluating LLMs reasoning ability in zero-shot setting and performance boosting through promptsNatural Language Processing Journal, 2023
- The performance of artificial intelligence language models in board-style dental knowledge assessmentThe Journal of the American Dental Association, 2023
- Dr. ChatGPT will see you now: How do Google and ChatGPT compare in answering patient questions on breast reconstruction?Journal of Plastic, Reconstructive & Aesthetic Surgery, 2023
- Quality of ChatGPT Responses to Questions Related To Liver TransplantationJournal of Gastrointestinal Surgery, 2023
- Analysis of large-language model versus human performance for genetics questionsEuropean Journal of Human Genetics, 2023
- Can ChatGPT be used in oral and maxillofacial surgery?Journal of Stomatology Oral and Maxillofacial Surgery, 2023
- The future of medical education and research: Is ChatGPT a blessing or blight in disguise?Medical Education Online, 2023
- ChatGPT: A comprehensive review on background, applications, key challenges, bias, ethics, limitations and future scopeInternet of Things and Cyber-Physical Systems, 2023