OpenAI's ChatGPT Passes Medical And MBA Exams ChatGPT passed the US Medical Licensing Examination (USMLE) which is an exam given by medical students to attain their license.
By Kavya Pillai
You're reading Entrepreneur India, an international franchise of Entrepreneur Media.
OpenAI's ChatGPT, the chatbot, has people astonished by its various use cases. One of the fields that the chatbot is proving to be a game changer is education. It appears that the ChatGPT is capable of doing a fine job with medical education. In a research paper, ChatGPT passed the US Medical Licensing Examination (USMLE) which is an exam given by medical students to attain their license.
As a matter of fact, the paper showed that the AI tool passed the exam that included three steps for the various levels of medical professions and also offered insights into the method followed to derive the answers. In December the first paper was published which showed that ChatGPT achieved more than 50% accuracy across all the exams and is available to read on medRxivopens. The researchers who worked on the paper wrote, "ChatGPT demonstrated a high level of concordance and insight in its explanations. These results suggest that large language models may have the potential to assist with medical education, and potentially, clinical decision-making."
The researchers, as part of their testing, relied on 376 test questions from the June 2022 sample exam which were publicly available. They also relied on "random spot checking" to make sure that "none of the answers, explanations, or related content were indexed on Google prior to January 1, 2022."
Currently, the AI tool's dataset is updated to 2021, as noted by the company OpenAI. What is interesting to know is that ChatGPT has managed to even pass the MBA exam which is designed by a Wharton professor from the University of Pennsylvania. The chatbot passed the exam by securing a B- and B grade.
Reportedly, the chatbot does an "amazing job at basic operations management and process analysis questions including those that are based on case studies," along with explanations. The AI tool is also good at "modifying its answers in response to human hints."
