POTENTIAL OF LARGE LANGUAGE MODEL CHAT GENERATIVE PRE-TRAINED TRANSFORMER IN CONSTRUCTING MULTIPLE CHOICE QUESTIONS ON PHARMACOLOGY OF DIABETES

Abstract

Objective: Creating high-quality multiple-choice questions (MCQs) is often a time-consuming and demanding process. This text aims to explore whether Chat generative pre-trained transformer (ChatGPT) can generate satisfactory MCQs on the topic of “pharmacology of diabetes.”

Methods: The ChatGPT, a large language model based on GPT technology, has been utilized as an artificial intelligence tool to create various types of MCQs. The answers generated by ChatGPT have been recorded for further analysis.

Results: ChatGPT generates pharmacology MCQs covering cognitive and affective domains with correct answers. It creates MCQs of varying difficulty, corrects mistakes, and can frame negative type and case-based MCQs. It generates three or four options unless specified otherwise.

Conclusion: ChatGPT can quickly generate high-quality MCQs but has limitations, including a lack of medical expertise, context comprehension, answer verification, and visual aid production. Teachers should validate ChatGPT-generated MCQs for accuracy and reliability, ensuring they align with the curriculum and include necessary context and visual aids for better comprehension.