Medical Teacher’s first ChatGPT’s referencing hallucinations: Lessons for editors, reviewers, and teachers
Abstract
Students’ inappropriate use of ChatGPT is a concern. There is also, however, the potential for academics to use ChatGPT inappropriately. After explaining ChatGPT’s “hallucinations” regarding citing and referencing, this commentary illustrates the problem by describing the detection of the first known Medical Teacher submission using ChatGPT inappropriately, the lessons that can be drawn from it for journal editors, reviewers, and teachers, and then the wider implications if this problem is left unchecked.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Numerous articles (5%) provide guidelines and "tips" on AI in medical education.
“Numerous articles (5%) provide guidelines and “tips” on AI in medical education [57, 83, 94, 135, 136, 162, 179, 186, 195, 196, 202, 205–210].”
From Artificial intelligence in undergraduate medical education: an updated scoping review (2025) · cites this paper as [94]
The tendency of generative AI systems to produce nonexistent references presents a substantial issue, and it can be challenging to discern when an AI system is generating misleading or inaccurate data.
“The tendency of these systems to produce nonexistent references presents a substantial issue, and it can be challenging to discern when an AI system is generating misleading or inaccurate data [1,21,25,27,28].”
From Opportunities, Challenges, and Future Directions of Generative Artificial Intelligence in Medical Education: Scoping Review (2023) · cites this paper as [21]
Generative AI has a propensity to hallucinate (create false information), and its knowledge is confined to its training data set.
“A significant issue lies in data accuracy, with many authors drawing attention to this technology’s propensity to “hallucinate,” or create false information, and its knowledge being confined to the training data set [1,10,21,22,25,27,28,34,37,44].”
From Opportunities, Challenges, and Future Directions of Generative Artificial Intelligence in Medical Education: Scoping Review (2023) · cites this paper as [21]
The citation lists haven’t been fetched yet
References 4 · Cited by 76
- Authors
- Masters, K.
- Affiliations
- Sultan Qaboos University (OM)
- Corresponding author
- Masters, Ken
- ORCID
- Masters, Ken
- Venue
- Medical Teacher
- Publisher
- Informa UK Limited
- Published
- 2023-05-15
- Volume
- 45
- Issue
- 7
- Pages
- 673-675
- ISSN
- 0142-159X (ISSN-L)
- 1466-187X
- OpenAlex
- W4376616652
- Cited by
- 76
- References
- 4
- Citations by year
- 2026: 12 · 2025: 32 · 2024: 21 · 2023: 11
- FWCI
- 19.06
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- Medical Teacher (publishedVersion)
- PubMed (publishedVersion)
- Topics
- Social Sciences › Safety Research › Academic integrity and plagiarism
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Physical Sciences › Computer Science › Information Systems › Artificial Intelligence in Education
- Keywords
- ChatGPT, hallucinations, referencing, citation, academic integrity, artificial intelligence in education, journal editors, peer reviewers, medical education, plagiarism detection
- MeSH terms
- Artificial Intelligence, Humans, Teaching
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
