Review
Version 1
Preserved in Portico This version is not peer-reviewed
Prompt Engineering in Medical Education
Version 1
: Received: 10 July 2023 / Approved: 12 July 2023 / Online: 12 July 2023 (12:04:42 CEST)
How to cite: Heston, T.F.; Khun, C. Prompt Engineering in Medical Education. Preprints 2023, 2023070813. https://doi.org/10.20944/preprints202307.0813.v1 Heston, T.F.; Khun, C. Prompt Engineering in Medical Education. Preprints 2023, 2023070813. https://doi.org/10.20944/preprints202307.0813.v1
Abstract
Artificial intelligence-powered generative language models (GLMs), such as ChatGPT and Google Bard, have the potential to provide personalized learning, unlimited practice opportunities, and interactive engagement 24/7, with immediate feedback. However, to fully utilize GLMs, properly formulated instructions are essential. Prompt engineering is a systematic approach to effectively communicating with GLMs to achieve the desired results. Well-crafted prompts yield good responses from the GLM, while poorly constructed prompts will lead to unsatisfactory responses. Besides the challenges of prompt engineering, significant concerns are associated with using GLMs in medical education, including ensuring accuracy, mitigating bias, maintaining privacy, and avoiding excessive reliance on technology. Future directions involve developing more sophisticated prompt engineering techniques, integrating GLMs with other technologies, creating personalized learning pathways, and researching the effectiveness of GLMs in medical education.
Keywords
ChatGPT, Artificial Intelligence, Medical Education
Subject
Medicine and Pharmacology, Other
Copyright: This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Comments (0)
We encourage comments and feedback from a broad range of readers. See criteria for comments and our Diversity statement.
Leave a public commentSend a private comment to the author(s)
* All users must log in before leaving a comment
