The role of large language models in the peer-review process: opportunities and challenges for medical journal reviewers and editors
Open accessThe DOI matches its Crossref record; 24 of the 24 references it cites were found in a registry or an index.
Abstract
The peer review process ensures the integrity of scientific research. This is particularly important in the medical field, where research findings directly impact patient care. However, the rapid growth of publications has strained reviewers, causing delays and potential declines in quality. Generative artificial intelligence, especially large language models (LLMs) such as ChatGPT, may assist researchers with efficient, high-quality reviews. This review explores the integration of LLMs into peer review, highlighting their strengths in linguistic tasks and challenges in assessing scientific validity, particularly in clinical medicine. Key points for integration include initial screening, reviewer matching, feedback support, and language review. However, implementing LLMs for these purposes will necessitate addressing biases, privacy concerns, and data confidentiality. We recommend using LLMs as complementary tools under clear guidelines to support, not replace, human expertise in maintaining rigorous peer review standards.
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
Liang, W., Zhang, Y., Cao, H., Wang, B., Ding, D., Yang, X., Vodrahalli, K., He, S., Smith, D., Yin, Y., et al. (2023) · arXiv · doi:10.48550/arxiv.2310.01783 · Cited by 633 · cited 1×
“In contrast, Liang et al. [15] reported more encouraging results from a large-scale study involving Nature portfolio journals and AI conference papers.”
AI and science: what 1,600 researchers think
Van Noorden, R., & Perkel, J. M. (2023) · Nature · doi:10.1038/d41586-023-02980-0 · Cited by 383 · cited 1×
“According to a Nature survey of 1,659 researchers [9], 11% of responders considered ex-pediting peer review as the primary benefit of generative AI, with 24% expecting this advantage to become the main function of generative AI in the future.”
The strain on scientific publishing
Hanson, M. A., Barreiro, P. G., Crosetto, P., & Brockington, D. (2024) · Quantitative Science Studies · doi:10.1162/qss_a_00327 · Cited by 345 · cited 1×
“The exponential increase in publications—up by 47% from 2016 to 2022—has outpaced the expansion of practicing scientists [3].”
The strain on scientific publishing
Hanson, M. A., Barreiro, P. G., Crosetto, P., & Brockington, D. (2023) · arXiv · doi:10.48550/arxiv.2309.15884 · Cited by 345
Hosseini, M., & Horbach, S. P. J. M. (2023) · Research Integrity and Peer Review · doi:10.1186/s41073-023-00133-5 · Cited by 328 · cited 1×
“Additionally, LLMs can refine the tone of review reports, facilitating more constructive and less aggressive comments [26].”
Ethics of large language models in medicine and medical research
Li, H., Moon, J. T., Purkayastha, S., Celi, L. A., Trivedi, H., & Gichoya, J. W. (2023) · The Lancet Digital Health · doi:10.1016/s2589-7500(23)00083-3 · Cited by 286 · cited 1×
“Many third-party LLM services rely on cloud-based processing systems with varying security protocols and data handling policies [31].”
Khraisha, Q., Put, S., Kappenberg, J., Warraitch, A., & Hadfield, K. (2024) · Research Synthesis Methods · doi:10.1002/jrsm.1715 · Cited by 269 · cited 1×
“Researchers have increasingly utilized AI tools for their scholarly work, such as literature reviews [5], data analysis [6], and manuscript writing [7].”
Khraisha, Q., Put, S., Kappenberg, J., Warraitch, A., & Hadfield, K. (2023) · arXiv · doi:10.48550/arxiv.2310.17526 · Cited by 268
Ganjavi, C., Eppler, M. B., Pekcan, A., Biedermann, B., Abreu, A., Collins, G. S., Gill, I. S., & Cacciamani, G. E. (2024) · BMJ · doi:10.1136/bmj-2023-077192 · Cited by 266 · cited 1×
“A study by Ganjavi et al. [33] showed a 25% increase in generative AI-related guidelines among the top 100 medical journals between March and October 2023, with growing attention to reviewer usage.”
Artificial intelligence in scientific writing: a friend or a foe?
Altmäe, S., Sola-Leyva, A., & Salumets, A. (2023) · Reproductive BioMedicine Online · doi:10.1016/j.rbmo.2023.04.009 · Cited by 174 · cited 1×
“Researchers have increasingly utilized AI tools for their scholarly work, such as literature reviews [5], data analysis [6], and manuscript writing [7].”
Potential of large language models in health care: Delphi study
Denecke, K., May, R., LLMHealthGroup, & Rivera Romero, O. (2024) · Journal of Medical Internet Research · doi:10.2196/52399 · Cited by 111
Exploring the potential of ChatGPT in the peer review process: an observational study
Saad, A., Jenko, N., Ariyaratne, S., Birch, N., Iyengar, K. P., Davies, A. M., Vaishya, R., & Botchu, R. (2024) · Diabetes & Metabolic Syndrome: Clinical Research & Reviews · doi:10.1016/j.dsx.2024.102946 · Cited by 80 · cited 3×
“For instance, while Saad et al. [14] used simple prompts requesting 3 advantages and disadvantages for each manuscript, other studies adopted more sophisticated methods, such as adopting specific reviewer personas or structured evaluation frameworks.”
Liang, W., Izzo, Z., Zhang, Y., Lepp, H., Cao, H., Zhao, X., Chen, L., Ye, H., Liu, S., Huang, Z., et al. (2024) · arXiv · doi:10.48550/arxiv.2403.07183 · Cited by 73 · cited 1×
“Liang et al. [13] developed a corpus-level detection model based on word distribution patterns and demonstrated LLM modification rates of 6.5% to 16.9% in AI conference peer reviews.”
InfluentialHow ChatGPT is transforming the postdoc experience
Nordling, L. (2023) · Nature · doi:10.1038/d41586-023-03235-8 · Cited by 71 · cited 1×
“[8].”
ChatGPT and the future of journal reviews: A feasibility study
Biswas, S., Dobaria, D., & Cohen, H. L. (2023) · The Yale Journal of Biology and Medicine · doi:10.59249/skdh9286 · Cited by 65
Mollaki, V. (2024) · Research Ethics · doi:10.1177/17470161231224552 · Cited by 64 · cited 1×
“This is especially beneficial for non-native English-speaking researchers, enabling proficient writing and reducing linguistic bias in academic publishing [28,29].”
Ng, J. Y., Maduranayagam, S. G., Suthakar, N., Li, A., Lokker, C., Iorio, A., Haynes, R. B., & Moher, D. (2025) · The Lancet Digital Health · doi:10.1016/s2589-7500(24)00202-4 · Cited by 64
Peer Review Matters: Research Quality and the Public Trust
Kharasch, E. D., Avram, M. J., Clark, J. D., Davidson, A. J., Houle, T. T., Levy, J. H., London, M. J., Sessler, D. I., & Vutskits, L. (2021) · Anesthesiology · doi:10.1097/aln.0000000000003608 · Cited by 60 · cited 1×
“This process is particularly important in the medical field, where research findings can directly affect patient care and treatment outcomes [2].”
Yin, S., Huang, S., Xue, P., Xu, Z., Lian, Z., Ye, C., Ma, S., Liu, M., Hu, Y., Lu, P., et al. (2025) · BMC Medicine · doi:10.1186/s12916-025-03899-1 · Cited by 43
ReviewerGPT? An Exploratory Study on Using Large Language Models for Paper Reviewing
Liu, R., & Shah, N. B. (2023) · arXiv · doi:10.48550/arxiv.2306.00622 · Cited by 23 · cited 1×
“Liu and Shah [17] found that GPT-4 could identify 7 out of 13 intentionally inserted errors in research papers, performing comparably to human reviewers.”
The AI Review Lottery: Widespread AI-Assisted Peer Reviews Boost Paper Scores and Acceptance Rates
Latona, G. R., Ribeiro, M. H., Davidson, T. R., Veselovsky, V., & West, R. (2024) · arXiv · doi:10.48550/arxiv.2405.02150 · Cited by 13
The AI Review Lottery: Widespread AI-Assisted Peer Reviews Boost Paper Scores and Acceptance Rates
Russo, G., Horta Ribeiro, M., Davidson, T. R., Veselovsky, V., & West, R. (2025) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3757667 · Cited by 12 · cited 1×
“A commercial LLM detection service estimated that at least 15.8% of reviews for an AI conference were written with AI assistance [12].”
InfluentialMARG: Multi-Agent Review Generation for Scientific Papers
D'Arcy, M., Hope, T., Birnbaum, L., & Downey, D. (2024) · arXiv · doi:10.48550/arxiv.2401.04259 · Cited by 9 · cited 1×
“D’Arcy et al. [16] proposed a multi-agent system approach, in which multiple AI agents with specialized roles collaborate to generate reviews, similar to the panel of human reviewers in traditional peer review systems.”
Is Your Paper Being Reviewed by an LLM? Investigating AI Text Detectability in Peer Review
Yu, S., Luo, M., Madasu, A., Lal, V., & Howard, P. (2024) · arXiv · doi:10.48550/arxiv.2410.03019 · Cited by 1 · cited 1×
“Detecting LLM-generated reviews is difficult due to 2 main obstacles: (1) authors often do not disclose their use of AI tools, and (2) current detection methods, even by human reviewers, are still unreliable due to high false positive or negative rates [11].”
Cited by
Can AI Be a Good Peer Reviewer? A Survey of Peer Review Process, Evaluation, and the Future
Wu, S., Jiang, O., Zhao, Y., Hu, T., Ma, Y., Zhang, K., Patwardhan, M., & Cohan, A. (2026) · Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/2026.acl-long.1504 · Cited by 11
Torrielli, F., Locci, S., Rapp, A., & Di Caro, L. (2026) · Scientometrics · doi:10.1007/s11192-026-05695-x · Cited by 8
Zhou, Q., Zhang, Z., Zhi, L., & Sun, L. (2026) · Findings of the Association for Computational Linguistics: EMNLP 2026 · doi:10.18653/2026.findings-emnlp.49 · Cited by 8
AI4Research: a survey of artificial intelligence for scientific research
Chen, Q., Yang, M., Qin, L., Liu, J., Yan, Z., Guan, J., Peng, D., Ji, Y., Li, H., Hu, M., et al. (2026) · Science China Information Sciences · doi:10.1007/s11432-025-5000-y · Cited by 4
Large Language Models as Peer Reviewers: Prompt Sensitivity and Model-Dependent Reproducibility
Erturk, S. M., & Durmaz, M. (2026) · Academic Radiology · doi:10.1016/j.acra.2026.04.046 · Cited by 5
Metadata
- Authors
- Lee, J., Lee, J., & Yoo, J.-J.
- Venue
- Journal of Educational Evaluation for Health Professions
- Published
- 2025-01-16
- Volume
- 22
- Pages
- 4
- ISSN
- 1738-1339 (ISSN-L)
- 1975-5937
- OpenAlex
- W4406408916
- Cited by
- 35
- References
- 24
- FWCI
- 7.17
- Type
- journal article
- Language
- en
- Open access
- diamond
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.