@Article{info:doi/10.2196/48305,
author="Epstein, Richard H
and Dexter, Franklin",
title="Variability in Large Language Models' Responses to Medical Licensing and Certification Examinations. Comment on ``How Does ChatGPT Perform on the United States Medical Licensing Examination? The Implications of Large Language Models for Medical Education and Knowledge Assessment''",
journal="JMIR Med Educ",
year="2023",
month="Jul",
day="13",
volume="9",
pages="e48305",
keywords="natural language processing; NLP; MedQA; generative pre-trained transformer; GPT; medical education; chatbot; artificial intelligence; AI; education technology; ChatGPT; Google Bard; conversational agent; machine learning; large language models; knowledge assessment",
issn="2369-3762",
doi="10.2196/48305",
url="https://mededu.jmir.org/2023/1/e48305",
url="https://doi.org/10.2196/48305",
url="http://www.ncbi.nlm.nih.gov/pubmed/37440293"
}