Leveraging Large Language Models to Generate Multiple-Choice Questions for Ophthalmology Education

Can a general-domain large language model (LLM) generate high-quality ophthalmology multiple choice questions (MCQs)?In this survey study, as evaluated by 10 independent ophthalmologists, LLM-MCQs were comparable in quality to those authored by a committee of human experts across 5 key domains: appropriateness, clarity and specificity, relevance, discriminative power, and suitability for trainees. Additionally, nearly 95% of LLM-MCQs had a similarity score less than 60 (on a scale where 100 indicates identical content), suggesting that most LLM-MCQs had limited or no resemblance to existing content.LLMs have the potential to enhance ophthalmology resident education through high-quality examination content generation.

Corresponding Author: Karine D. Bojikian, MD, PhD, Department of Ophthalmology, University of Washington, Box 359608, 325 Ninth Ave, Seattle, WA 98104-2499 (bkarine@uw.edu).

Link to the article in your story

We encourage you to link out to this article in your story using the link below. It includes an access token that will give free access to the article for your readers up to one year after publication. (The link will be live after the article publishes and embargo is lifted.)

Please see the article for additional information, including full author list, author contributions and affiliations, conflict of interest and financial disclosures, and funding and support.

Need more information? Contact us.