Ten simple rules for using large language models in science, version 1.0
The DOI matches its Crossref record, with a small difference in title or year; 19 of the 19 references it cites were found in a registry or an index.
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.
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
“yet existing guidance treats prompting and verification as separate topics rather than as integrated components of a single risk management framework”
From A practical risk framework for large language model use in life science research (2026) · cites this paper as [10]
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 biomass distribution on Earth
Bar-On, Y. M., Phillips, R., & Milo, R. (2018) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1711842115 · Cited by 3,723 · cited 1×
“The estimate of 450 Gt C can instead be traced to Bar-On and colleagues (2018) [24].”
BackgroundGreening of the Earth and its drivers
Zhu, Z., Piao, S., Myneni, R. B., Huang, M., Zeng, Z., Canadell, J. G., Ciais, P., Sitch, S., Friedlingstein, P., Arneth, A., et al. (2016) · Nature Climate Change · doi:10.1038/nclimate3004 · Cited by 2,779
An ecoregion-based approach to protecting half the terrestrial realm
Dinerstein, E., Olson, D., Joshi, A., Vynne, C., Burgess, N. D., Wikramanayake, E., Hahn, N., Palminteri, S., Hedao, P., Noss, R., et al. (2017) · BioScience · doi:10.1093/biosci/bix014 · Cited by 2,460 · cited 1×
“Here, the user provides ChatGPT with Google Earth Engine code (rendered as [ . . . ] in the example) that is meant to perform a set of statistical aggregation and spatial calculations within ecoregions [36] but is instead returning an error.”
MethodA constant error in psychological ratings.
Thorndike, E. L. (1920) · Journal of Applied Psychology · doi:10.1037/h0071663 · Cited by 2,163
ChatGPT: five priorities for research
van Dis, E. A. M., Bollen, J., Zuidema, W., van Rooij, R., & Bockting, C. L. (2023) · Nature · doi:10.1038/d41586-023-00288-7 · Cited by 1,842
Gray literature: An important resource in systematic reviews
Paez, A. (2017) · Journal of Evidence-Based Medicine · doi:10.1111/jebm.12266 · Cited by 1,459
ChatGPT is fun, but not an author
Thorp, H. H. (2023) · Science · doi:10.1126/science.adg7879 · Cited by 1,437
Perkins, M. (2023) · Journal of University Teaching and Learning Practice · doi:10.53761/1.20.02.07 · Cited by 839
What ChatGPT and generative AI mean for science
Stokel-Walker, C., & Van Noorden, R. (2023) · Nature · doi:10.1038/d41586-023-00340-6 · Cited by 828 · cited 2×
“In addition to transforming the world economy [1], generative AI tools like LLMs will likely transform the way we do science [5].”
BackgroundReviewer bias in single- versus double-blind peer review
Tomkins, A., Zhang, M., & Heavlin, W. D. (2017) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1707323114 · Cited by 605 · cited 1×
“Coupled with journal adoption of double-blind reviewing practices [31], an LLM can help to address this problem by copyediting manuscripts and other communication to ensure that English is used idiomati-cally [32], reducing opportunities for bias from referees.”
Background
Research works printed but not linked: 20
- J Hatzius, 2023, The Potentially Large Effects of Artificial Intelligence on Economic Growth
- K. Hu, 2023, ChatGPT sets record for fastest-growing user base—analyst note, Reuters.
- T Harris, 2023, The A.I. Dilemma., United States of America: Center for Humane Technology
- L Weidinger, 2022, Taxonomy of Risks posed by Language Models. ACM International Conference Proceeding Series, Association for Computing Machinery, 214
- The AI writing on the wall, 2023, Nat Mach Intell, 5, 1, 10.1038/s42256-023-00613-9 · DOI
- RV Yampolskiy, 2019, Unpredictability of AI., ArXiv.
- L Derczynski, 2023, Assessing Language Model Deployment with Risk Cards., ArXiv
- D. Leslie, 2023, Does the sun rise for ChatGPT? Scientific discovery in the age of generative AI., AI and Ethics
- BA Anders, 2023, Is using ChatGPT cheating, plagiarism, both, neither, or forward thinking?, Patterns., 4, 100694, 10.1016/j.patter.2023.100694 · DOI · Paper page
- Y. Markovski, 2023, How your data is used to improve model performance
- J van den Hoogen, 2019, Soil nematode abundance and functional group composition at a global scale, Nature, 572, 194, 10.1038/s41586-019-1418-6 · DOI · Paper page
- D Gough, 2017, An Introduction to Systematic Reviews
- E Ladouceur, 2022, Knowledge sharing for shared success in the decade on ecosystem restoration., Ecol Solut Evid., 3
- OM Smith, 2023, Peer review perpetuates barriers for historically excluded groups., Nat Ecol Evol.
- AL Romero-Olivares, 2019, Researchers, don’t be rude to nonnative English speakers, Science
- GR Smith, 2019, Building a global database of soil microbial biomass and function: a call for collaboration., Soil Org., 91, 140
- JEM van der Wal, 2021, Collaboration enhances career progression in academic science, especially for female researchers., Proc Biol Sci., 288, 20210219
- C Merow, 2023, AI chatbots can boost scientific coding., Nat Ecol Evol., 960, 10.1038/s41559-023-02063-3 · DOI
- SJ Ahmed, 2022, An Analysis of Writer’s Block: Causes and Solutions., Creat Res J, 34, 339, 10.1080/10400419.2022.2031436 · DOI
- EM Bender, 2021, On the dangers of stochastic parrots: Can language models be too big? FAccT 2021—Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency, Association for Computing Machinery, Inc, 610
Cited by
A practical risk framework for large language model use in life science research
Sharpton, T., Davis II, E. W., & Alexiev, A. (2026) · PLOS Computational Biology · doi:10.1371/journal.pcbi.1014776
Metadata
- Authors
- Smith, G. R., Bello, C., Bialic-Murphy, L., Clark, E., Delavaux, C. S., Fournier de Lauriere, C., van den Hoogen, J., Lauber, T., Ma, H., Maynard, D. S., Mirman, M., Mo, L., Rebindaine, D., Reek, J. E., Werden, L. K., Wu, Z., Yang, G., Zhao, Q., Zohner, C. M., & Crowther, T. W.
- ORCID
- Venue
- PLOS Computational Biology
- Publisher
- Public Library of Science (PLoS)
- Published
- 2024-01-31
- Volume
- 20
- Issue
- 1
- Pages
- e1011767
- ISSN
- 1553-7358
- Cited by
- 25
- References
- 19
- Language
- en
- Funders
- DOB Ecology
- Bernina Initiative
- Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung (TMPFP3_209925, PZ00P3_193612, PZ00P3_193646, PZ00P3_216194)
- Ministère des Affaires Etrangères (102390W)
- China Scholarship Council (202206040112, 202206850027)
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.