Learning to Fake It: Limited Responses and Fabricated References Provided by ChatGPT for Medical Questions
Objective: To evaluate the quality of the answers and the references provided by ChatGPT for medical questions. Patients and Methods: Three researchers asked ChatGPT 20 medical questions and prompted it to provide the corresponding references. The responses were evaluated for the quality of content...
Main Authors: | Jocelyn Gravel, MD, MSc, Madeleine D’Amours-Gravel, Esli Osmanlliu, MD, MSc |
---|---|
Format: | Article |
Language: | English |
Published: |
Elsevier
2023-09-01
|
Series: | Mayo Clinic Proceedings: Digital Health |
Online Access: | http://www.sciencedirect.com/science/article/pii/S2949761223000366 |
Similar Items
-
ChatGPT's responses to gout-related questions
by: Daorong Hong, et al.
Published: (2023-12-01) -
with ChatGPT
by: David Szanto
Published: (2024-03-01) -
Is medicine ready for ChatGPT – why not just ask ChatGPT?
by: Anthony Rodigin
Published: (2023-04-01) -
Is medicine ready for ChatGPT – why not just ask ChatGPT?
by: Anthony Rodigin
Published: (2023-06-01) -
ChatGPT's responses to rheumatoid arthritis-related questions
by: Chunyan Huang, et al.
Published: (2023-12-01)