Uncategorized

Performance of Generative Large Language Models on Ophthalmology Board Style Questions



We have received the comment by Kleebayoon and Wiwanitkit and thank them for the time spent reviewing our recent article. The purpose of this study was to highlight the limitations of using chat-based language models to answer ophthalmology questions, which we succeeded with using the number of questions that we sampled. At the time of the study and at the time of this comment, Bing Chat and ChatGPT 4.0 remain the 2 strongest publicly available large language models in their ability to answer medical challenge questions.

Source: American Journal of Ophthalmology Category: Opthalmology Authors: Tags: Correspondence Source Type: research



Source link

Leave a Reply

Your email address will not be published. Required fields are marked *