A practical risk framework for large language model use in life science research
Open accessThe DOI matches its Crossref record; 27 of the 27 references it cites were found in a registry or an index; none of the 26 sources its claims cite is checked for support yet.
Abstract
Responsible use of large language models (LLMs) in life science research demands a unified approach to risk, yet existing guidance treats prompting and verification as separate topics rather than as integrated components of a single risk management framework. This paper addresses that gap for life science researchers. We explain how LLM architecture produces both remarkable capabilities and characteristic failures including hallucination and sycophancy, with particular attention to vulnerabilities most relevant to life science workflows. We argue that effective prompt design is itself a primary risk management strategy, reducing the probability and severity of characteristic failures before verification is required, and introduce a structured framework for matching downstream verification effort to risk across dimensions of output verifiability, researcher expertise, and consequence of error. We apply both layers to common research tasks, including literature synthesis, code generation, writing assistance, statistical reasoning, and administrative work, with documentation practices and ethical obligations addressed throughout. Six supplementary guides extend each component into detailed workflows, worked examples, and reference checklists, and a companion open-source repository ( https://github.com/SharptonLab/PromptLab ) provides tested prompts and verification tools for immediate use. Together, these resources are designed to help researchers use these tools carefully and document how they did so.
Overview
CoChat Summary
TL;DR
The paper proposes a practical, integrated risk framework for LLM use in life science research that pairs upstream prompt design with downstream verification calibrated to output verifiability, researcher expertise, and consequence of error. It applies the framework to literature synthesis, code generation, writing assistance, statistical reasoning, and administrative tasks, and provides supplementary guides plus an open-source PromptLab repository.
Key findings
- Prompt design is treated as primary upstream risk management, while verification handles residual risk; verification effort scales across three dimensions—verifiability, domain expertise, and consequence of error—with low-stakes outputs within expertise warranting spot-checking, publication-bound or high-stakes outputs requiring systematic verification, and outputs outside expertise requiring external validation.
- The framework identifies four characteristic failure modes—hallucination, sycophancy, overconfidence, and plausible but incorrect reasoning—and maps each to an upstream prompt constraint and the downstream verification still required.
- It applies the framework to common tasks: literature synthesis (citation fabrication is an ever-present hazard; never ask the model to verify its own citations), code generation (most favorable risk profile because code is directly testable, but risk is code that runs yet produces wrong results), statistical reasoning (treat model suggestions as starting points and consult a statistician for publication-central analyses), and administrative tasks (highest-value, lowest-risk application).
- The companion PromptLab repository provides 24 runnable prompts tested across six models, with all three authors independently reviewing outputs against the repository’s verification checklist; errors were infrequent, model-specific, and of the kinds described, though this was an internal check rather than a benchmark. Six supplementary guides (S1–S6 Files) extend the components.
Methods
- Design: conceptual/perspective framework paper, not a primary empirical study; it develops an integrated risk framework and applies it to life science research tasks.
- Data/sample: an open-source PromptLab repository with 24 runnable prompts; prompts were tested across a six-model panel (Claude Sonnet 4.6, Claude Opus 4.7, GPT-5.5, Gemini 2.5 Pro, Nemotron 3 Super 120B, and Step-3.7 Flash), captured on 2026-06-25 at temperature 0.0 where accepted, with reasoning-capable models using provider defaults.
- Analysis: no formal statistical analysis is reported; repository testing is described as an internal check, with full per-model and per-cell results archived with the repository (Zenodo DOI 10.5281/zenodo.21170206).
Limitations
- The paper states that the repository testing was an internal check rather than a benchmark, and that a larger, controlled evaluation remains useful future work.
- The paper states that context windows change rapidly and avoids citing a specific figure; it also notes that the empirical picture on hallucination rates is still developing and that some prompting techniques matter less as models improve.
- Evident from the text: no quantitative error rates or controlled comparison are reported, and the verification framework is conceptual and not empirically validated; the repository evaluation relies on author review against a checklist rather than independent benchmarking.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Figures


Verification
Claims the paper makes
0 Valid · 3 Not valid · 12 Not checked · 87 Own results and interpretations
A check of a cited source is scheduled, or we don’t hold its full text yet; the claim is checked once it runs.
In the paper
“yet existing guidance treats prompting and verification as separate topics rather than as integrated components of a single risk management framework”
- Also stated in: § 1. Introduction · plain
“What remains missing is guidance on how to prioritize the verification of model outputs, so that checking accuracy does not expand into an unmanageable burden.”
§ A practical risk framework for large language model use in life science research > Abstract
What the sources say
- Not checked yetcites [3] L Giray, 2023, Prompt Engineering with ChatGPT: a guide for academic writers, Ann Biomed Eng source
A check is scheduled.
- Not checked yetcites [4] S Schulhoff, 2024 source
A check is scheduled.
- Not checked yetcites [5] CJ Brown, 2026, Prompting LLMs for quality ecological statistics, Methods Ecol Evol source
A check is scheduled.
- Not checked yetcites [10] GR Smith, 2024, Ten simple rules for using LLMs in science, PLOS Comput Biol source
A check is scheduled.
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Also stated in: § 1. Introduction · plain
A check of a cited source is scheduled, or we don’t hold its full text yet; the claim is checked once it runs.
In the paper
“While this process helps produce a useful tool, it also induces sycophancy, a systematic tendency to agree with users and avoid contradiction [12,13].”
- Also stated in: § Box 1. Key terms for LLM use in life science research. Definitions emphasize practical consequences for researchers rather than technical precision; cross-references indicate where each concept is discussed in detail. · plain
“Sycophancy. A systematic tendency to agree with users, confirm hypotheses, and avoid contradiction, resulting from training processes that reward helpful-seeming responses.”
§ A practical risk framework for large language model use in life science research > 2. How LLMs work
What the sources say
- Not checked yetcites [12] Sharma M, Tong M, Korbak T. Towards understanding sycophancy in language models. In: ICLR 2024, 2024. https://doi.org/arXiv:2310.13548
A check is scheduled.
- Not checked yetcites [13] Perez E, Ringer S, Lukosiute K, Nguyen K, Chen E, Heiner S, et al. Discovering language model behaviors with model-written evaluations. In: Findings of the Association for Computational Linguistics: ACL 2023, 2023. p. 13387–434. https://doi.org/10.18653/v1/2023.findings-acl.847 source
A check is scheduled.
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Also stated in: § Box 1. Key terms for LLM use in life science research. Definitions emphasize practical consequences for researchers rather than technical precision; cross-references indicate where each concept is discussed in detail. · plain
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“prompt constraints specifying expected input/output behavior, edge case handling, and required documentation reduce the likelihood of silently incorrect implementations”
§ A practical risk framework for large language model use in life science research > 5. Research applications
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“We argue that effective prompt design is itself a primary risk management strategy, reducing the probability and severity of characteristic failures before verification is required”
§ A practical risk framework for large language model use in life science research > Abstract
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: unclear — It is unclear why the paper says it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“For systematic research tasks, constraining output to defined schemas (such as JSON with explicit field names, data types, acceptable values, and a confidence flag) transforms the model from a prose generator into a structured information extraction tool.”
§ A practical risk framework for large language model use in life science research > 3. Effective prompting as upstream risk management
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
3 more claims
Create a free account to see all 102 claims and to verify the 26 references still open.
- Probably not a substantial claim. 76
- It may state two separate claims as one. 56
Citations
Cites
Language Models are Few-Shot Learners
Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.14165 · Cited by 23,372
Survey of Hallucination in Natural Language Generation
Ji, Z., Lee, N., Frieske, R., Yu, T., Su, D., Xu, Y., Ishii, E., Bang, Y. J., Madotto, A., & Fung, P. (2023) · ACM Computing Surveys · doi:10.1145/3571730 · Cited by 5,025 · cited 1×
“Asked for a reference, it may generate citation-like text whether that citation exists or not, reproducing associations from training even where they do not apply [14,15].”
Huang, L., Yu, W., Ma, W., Zhong, W., Feng, Z., Wang, H., Chen, Q., Peng, W., Feng, X., Qin, B., et al. (2025) · ACM Transactions on Information Systems · doi:10.1145/3703155 · Cited by 4,688 · cited 1×
“Asked for a reference, it may generate citation-like text whether that citation exists or not, reproducing associations from training even where they do not apply [14,15].”
Chain-Of-Thought Prompting Elicits Reasoning in Large Language Models
Wei, J., Wang, X., Schuurmans, D., Bosma, M., Ichter, B., Xia, F., Chi, E., Le, Q. V., & Zhou, D. (2022) · Advances in Neural Information Processing Systems 35 · doi:10.52202/068431-1800 · Cited by 4,505 · cited 1×
“Chain-of-thought prompting, asking the model to work through a problem step by step, often improves performance on reasoning tasks [16] and makes intermediate reasoning visible for inspection.”
Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
Wei, J., Wang, X., Schuurmans, D., Bosma, M., Ichter, B., Xia, F., Chi, E., Le, Q., & Zhou, D. (2022) · arXiv · doi:10.48550/arxiv.2201.11903 · Cited by 4,263
Lost in the Middle: How Language Models Use Long Contexts
Liu, N. F., Lin, K., Hewitt, J., Paranjape, A., Bevilacqua, M., Petroni, F., & Liang, P. (2024) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00638 · Cited by 1,612 · cited 1×
“Even within a large window, models attend unevenly across long inputs [11], so fitting material into the window does not guarantee the model uses it.”
Sharma, M., Tong, M., Korbak, T., Duperrouzel, D., Was, H., Korbak, J., Cheng, M., Askell, A., Bai, Y., Brain, C., et al. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2310.13548 · Cited by 1,313
Prompt Engineering with ChatGPT: A Guide for Academic Writers
Giray, L. (2023) · Annals of Biomedical Engineering · doi:10.1007/s10439-023-03272-4 · Cited by 776
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
LLM Evaluators Recognize and Favor Their Own Generations
Panickssery, A., Bowman, S. R., & Feng, S. (2024) · arXiv · doi:10.48550/arxiv.2404.13076 · Cited by 559
Research works printed but not linked: 4
- Sharma M, Tong M, Korbak T. Towards understanding sycophancy in language models. In: ICLR 2024, 2024. https://doi.org/arXiv:2310.13548
- Nature Portfolio. Artificial intelligence (AI). Nature Portfolio Editorial Policies. 2024. Available from: https://www.nature.com/nature-portfolio/editorial-policies/ai
- PLOS. Ethical publishing practice. PLOS ONE Editorial Policies. 2024. Available from: https://journals.plos.org/plosone/s/ethical-publishing-practice
- Elsevier. The use of generative AI and AI-assisted technologies in the editorial process. 2024. Available from: https://www.elsevier.com/about/policies-and-standards/
Cited by
Still being checked.
Metadata
- Authors
- Sharpton, T., Davis II, E. W., & Alexiev, A.
- Affiliations
- Oregon State University (US)
- Oregon State University
- Corresponding author
- Sharpton, Thomas
- Venue
- PLOS Computational Biology
- Publisher
- Public Library of Science (PLoS)
- Published
- 2026-09-16
- Volume
- 22
- Issue
- 9
- Pages
- e1014776
- ISSN
- 1553-734X (ISSN-L)
- 1553-7358
- PMC
- PMC13581008
- OpenAlex
- W7213427123
- Semantic Scholar
- e0b39f790beedccef8c368ccede1b6eca9232cd9
- Cited by
- 0
- References
- 24
- FWCI
- 0.00
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- PLoS Computational Biology (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion)
- Funders
- National Science Foundation (2025457)
- Oregon State University
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Ethics and Social Impacts of AI
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Physical Sciences › Computer Science › Artificial Intelligence › Artificial Intelligence Applications
- Keywords
- large language models, risk management framework, life science research, prompt engineering, hallucinations, sycophancy, output verification, research ethics, literature synthesis, code generation, statistical reasoning, research documentation
- MeSH terms
- Large Language Models, Biological Science Disciplines, Humans, Risk Management, Computational Biology, Workflow
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.
A language model drew the claims from the paper on 2026-11-21, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-11-21 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
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: A practical risk framework for large language model use in life science research. https://app.cochat.ai/papers/10.1371/journal.pcbi.1014776
- The paper
- Sharpton, T., Davis II, E. W., & Alexiev, A. (2026). A practical risk framework for large language model use in life science research. PLOS Computational Biology. https://doi.org/10.1371/journal.pcbi.1014776
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.