ChatGPT for assessment writing
The DOI matches its Crossref record; 3 of the 3 references it cites were found in a registry or an index.
Abstract
What is the educational challenge?Medical schools invest significant resources into the creation of multiple-choice items for assessments. This process is costly and requires faculty training. Recently ChatGPT has been used in various areas to improve content creation efficiency, and it has otherwise been used to answer USMLE-style assessment items.What are the proposed solutions?We proposed the use of ChatGPT to create initial drafts of multiple-choice items.What are the potential benefits to a wider global audience?The use of ChatGPT to generate assessment items can decrease resources required, allowing for the creation of more items, and freeing-up faculty time to perform higher level assessment activities. ChatGPT is also able to consistently produce items using a standard format while adhering to item writing guidelines, which can be very challenging for faculty teams.What are the next steps?We plan to pilot ChatGPT drafted questions and compare item statistics for those written by ChatGPT with those written by our content experts. We also plan to further identify the types of questions that ChatGPT is most appropriate for, and incorporate media into assessment items (e.g. images, videos).
Overview
Integrity signals
Registry
Cites
Statistics
Verification
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?
In the citing paper
“The creation of high-quality MCQs is a time-consuming task [5, 6], even more considering that changes in the curriculum or students collecting questions from previous years requires teachers to create new sets of questions every once in a while [7].”
From Docimological Quality Analysis of LLM-Generated Multiple Choice Questions in Computer Science and Medicine (2024) · cites this paper as [7]
In the citing paper
“Nevertheless, MCQs are the most common type of knowledge assessment [5], e.g., in medical education [7].”
From Docimological Quality Analysis of LLM-Generated Multiple Choice Questions in Computer Science and Medicine (2024) · cites this paper as [7]
In the citing paper
“Content experts remain responsible for checking the accuracy of the generated questions, and while editing is certainly necessary, it takes less time to edit generated questions than to create them from scratch [6, 7].”
From Docimological Quality Analysis of LLM-Generated Multiple Choice Questions in Computer Science and Medicine (2024) · cites this paper as [7]
In the citing paper
“Content experts remain responsible for checking the accuracy of the generated questions, and while editing is certainly necessary, it takes less time to edit generated questions than to create them from scratch [6, 7].”
From Docimological Quality Analysis of LLM-Generated Multiple Choice Questions in Computer Science and Medicine (2024) · cites this paper as [7]
Citations
Cites
Gilson, A., Safranek, C. W., Huang, T., Socrates, V., Chi, L., Taylor, R. A., & Chartash, D. (2023) · JMIR Medical Education · doi:10.2196/45312 · Cited by 2,078
The Quality of In-house Medical School Examinations
Jozefowicz, R. F., Koeppen, B. M., Case, S., Galbraith, R., Swanson, D., & Glew, R. H. (2002) · Academic Medicine · doi:10.1097/00001888-200202000-00016 · Cited by 164
ChatGPT in medical school: how successful is AI in progress testing?
Friederichs, H., Friederichs, W. J., & März, M. (2023) · Medical Education Online · doi:10.1080/10872981.2023.2220920 · Cited by 122 · cited 1×
“While AI has been able to correctly answer USMLE-style assessment items, there is a potential to use ChatGPT (OpenAI, San Francisco) to reduce resources required for item generation while ensuring standardized item creation (Friederichs et al. 2023; Gilson et al. 2023).”
Method
Research works printed but not linked: 2
- Billings MS, DeRuchie K, Hussie K, Kulesher A, Merrell J, Morales A, Paniagua MA, Sherlock J, Swygert KA, Tyson J. 2020. NBME item-writing guide: constructing written test questions for the health sciences. Philadelphia: NBME.
- Wilkinson D. 2023. Be careful… ChatGPT appears to be making up academic references. The Oxford Review. https://oxford-review.com/chatgpt-making-up-references/.
Cited by
Lai, C. Y., Cheung, K. Y., Chan, C. S., & Law, K. K. (2024) · Computers and Education: Artificial Intelligence · doi:10.1016/j.caeai.2024.100246 · Cited by 122
LLM-based automatic short answer grading in undergraduate medical education
Grévisse, C. (2024) · BMC Medical Education · doi:10.1186/s12909-024-06026-5 · Cited by 93
Coşkun, Ö., Kıyak, Y. S., & Budakoğlu, I. İ. (2025) · Medical Teacher · doi:10.1080/0142159x.2024.2327477 · Cited by 64
Kıyak, Y. S., & Kononowicz, A. A. (2024) · Medical Teacher · doi:10.1080/0142159x.2024.2314723 · Cited by 53
Grévisse, C., Pavlou, M. A. S., & Schneider, J. G. (2024) · SN Computer Science · doi:10.1007/s42979-024-02963-6 · Cited by 41
“Zuckerman et al. used ChatGPT 2 to create USMLE 3 -style MCQ items with a clinical vignette, vital signs and exam findings [7].”
Influential
Metadata
- Authors
- Zuckerman, M., Flood, R., Tan, R. J. B., Kelp, N., Ecker, D. J., Menke, J., & Lockspeiser, T.
- Affiliations
- University of Colorado Anschutz (US)
- Children's Hospital Colorado (US)
- Corresponding author
- Zuckerman, Matthew
- Venue
- Medical Teacher
- Publisher
- Informa UK Limited
- Published
- 2023-10-03
- Volume
- 45
- Issue
- 11
- Pages
- 1224-1227
- ISSN
- 0142-159X (ISSN-L)
- 1466-187X
- OpenAlex
- W4387327237
- Cited by
- 83
- References
- 3
- Citations by year
- 2026: 17 · 2025: 29 · 2024: 36 · 2023: 1
- FWCI
- 3.27
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- Medical Teacher (publishedVersion)
- PubMed (publishedVersion)
- Topics
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Social Sciences › Education › Innovations in Medical Education
- Social Sciences › Education › Artificial Intelligence in Education
- Keywords
- ChatGPT, automated item generation, medical school assessment, faculty workload, item writing guidelines, large language models in education
- MeSH terms
- Educational Status, Faculty, Humans, Schools, Medical, Videotape Recording, Writing
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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: ChatGPT for assessment writing. https://app.cochat.ai/papers/10.1080/0142159x.2023.2249239
- The paper
- Zuckerman, M., Flood, R., Tan, R. J. B., Kelp, N., Ecker, D. J., Menke, J., & Lockspeiser, T. (2023). ChatGPT for assessment writing. Medical Teacher. https://doi.org/10.1080/0142159x.2023.2249239
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.