How much can we rely on artificial intelligence chatbots such as the ChatGPT software program to assist with scientific writing?
The DOI matches its Crossref record; 7 of the 7 references it cites were found in a registry or an index.
Abstract
STATEMENT OF PROBLEM: Use of the ChatGPT software program by authors raises many questions, primarily regarding egregious issues such as plagiarism. Nevertheless, little is known about the extent to which artificial intelligence (AI) models can produce high-quality research publications and advance and shape the direction of a research topic. PURPOSE The purpose of this study was to determine how well the ChatGPT software program, a writing tool powered by AI, could respond to questions about scientific or research writing and generate accurate references with academic examples. MATERIAL AND METHODS Questions were made for the ChatGPT software program to locate an abstract containing a particular keyword in the Journal of Prosthetic Dentistry (JPD). Then, whether the resulting articles existed or were published was determined. Questions were made for the algorithm 5 times to locate 5 JPD articles containing 2 specific keywords, bringing the total number of articles to 25. The process was repeated twice, each time with a different set of keywords, and the ChatGPT software program provided a total of 75 articles. The search was conducted at various times between April 1 and 4, 2023. Finally, 2 authors independently searched the JPD website and Google Scholar to determine whether the articles provided by the ChatGPT software program existed. RESULTS When the author tested the ChatGPT software program's ability to locate articles in the JPD and Google Scholar using a set of keywords, the results did not match the papers that the ChatGPT software program had generated with the help of the AI tool. Consequently, all 75 articles provided by the ChatGPT software program were not accurately located in the JPD or Google Scholar databases and had to be added manually to ensure the accuracy of the relevant references. CONCLUSIONS Researchers and academic scholars must be cautious when using the ChatGPT software program because AI-generated content cannot provide or analyze the same information as an author or researcher. In addition, the results indicated that writing credit or references to such content or references in prestigious academic journals is not yet appropriate. At this time, scientific writing is only valid when performed manually by researchers.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
The global landscape of AI ethics guidelines
Jobin, A., Ienca, M., & Vayena, E. (2019) · Nature Machine Intelligence · doi:10.1038/s42256-019-0088-2 · Cited by 6,220
Ethics of AI in Education: Towards a Community-Wide Framework
Holmes, W., Porayska-Pomsta, K., Holstein, K., Sutherland, E., Baker, T., Shum, S. B., Santos, O. C., Rodrigo, M. T., Cukurova, M., Bittencourt, I. I., et al. (2022) · International Journal of Artificial Intelligence in Education · doi:10.1007/s40593-021-00239-1 · Cited by 1,437
ChatGPT is fun, but not an author
Thorp, H. H. (2023) · Science · doi:10.1126/science.adg7879 · Cited by 1,437
ChatGPT listed as author on research papers: many scientists disapprove
Stokel-Walker, C. (2023) · Nature · doi:10.1038/d41586-023-00107-z · Cited by 868
Haleem, A., Javaid, M., & Singh, R. P. (2022) · BenchCouncil Transactions on Benchmarks, Standards and Evaluations · doi:10.1016/j.tbench.2023.100089 · Cited by 694
Tools such as ChatGPT threaten transparent science; here are our ground rules for their use
(2023) · Nature · doi:10.1038/d41586-023-00191-1 · Cited by 605
Plagiarism in the age of massive generative pre-trained transformers (GPT-3)
Dehouche, N. (2021) · Ethics in Science and Environmental Politics · doi:10.3354/esep00195 · Cited by 296
Cited by
Akiba, D., & Fraboni, M. C. (2023) · Education Sciences · doi:10.3390/educsci13090885 · Cited by 115
Current status of ChatGPT use in medical education: potentials, challenges, and strategies
Xu, T., Weng, H., Liu, F., Yang, L., Luo, Y., Ding, Z., & Wang, Q. (2024) · Journal of Medical Internet Research · doi:10.2196/57896 · Cited by 84
Khampusaen, D. (2025) · LEARN Journal: Language Education and Acquisition Research Network · doi:10.70730/pgcq9242 · Cited by 31
Does ChatGPT Ignore Article Retractions and Other Reliability Concerns?
Thelwall, M., Lehtisaari, M., Katsirea, I., Holmberg, K., & Zheng, E. (2025) · Learned Publishing · doi:10.1002/leap.2018 · Cited by 18
Lin, A., Chen, Z., Jiang, A., Tang, B., Qi, C., Zhu, L., Mou, W., Gan, W., Zeng, D., Xiao, M., et al. (2026) · International Journal of Surgery · doi:10.1097/js9.0000000000003839 · Cited by 2
Metadata
- Authors
- Dashti, M., Londono, J., Ghasemi, S., & Moghaddasi, N.
- Venue
- The Journal of Prosthetic Dentistry
- Publisher
- Elsevier BV
- Published
- 2025-04
- Volume
- 133
- Issue
- 4
- Pages
- 1082-1088
- ISSN
- 0022-3913 (ISSN-L)
- OpenAlex
- W4383751841
- Cited by
- 50
- References
- 7
- FWCI
- 43.79
- Type
- journal article
- Language
- en
- Open access
- closed
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
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.