Use of an artificial intelligence application as a source of information for solving Dentistry exams

Abstract

Introduction: ChatGPT is a public tool developed by OpenAI that employs the language model technology of GPT. This chatbot is capable of addressing various text-based requests. Objective: To assess whether ChatGPT can be the sole source of information for resolving Dentistry exams. Materials and Methods: This is an analytical quantitative cross-sectional study. For data collection, a fictitious exam was created, consisting of questions from the National Student Performance Exam (ENADE) and other public competitions. Participants answered the exam at two different times: T1, without ChatGPT, and, after 15 days (T2), using it. The sample included 30 undergraduate Dentistry students, equally divided into three groups: 1st to 4th semester, 5th to 6th semester, and 7th to 10th semester. Descriptive and inferential statistical analyses were applied using SPSS software, including the Wilcoxon and McNemar tests. Results: They revealed a notable effectiveness of ChatGPT in resolving essay questions, with an 83.3% accuracy rate, while students provided more incorrect or incomplete answers. However, limitations of the ChatGPT database were observed regarding objective questions. It is crucial to emphasize that, despite promising results, the application of Chat raises ethical and pedagogical questions. Therefore, the introduction of ChatGPT in education raises concerns about the validity and fairness of assessments, underscoring the importance of finding a balance between technological innovation and the preservation of academic integrity.