Skip to content
DraconiticResearch
Search Sources API
226,742 studies31 sourcesUpdated 50 min ago
Peer-reviewedCC BYLife science alliance

LLM tool use in manuscript review: Toward guidance and transparency.

  1. 1Cancer Data Science Laboratory, Center for Cancer Research, National Cancer Institute, National Institutes of Health, Bethesda, MD, USA [email protected].
  2. 2Department of Natural Science, College of Arts, Sciences and Letters, University of Michigan-Dearborn, Dearborn, MI, USA.
  3. 3Cancer Data Science Laboratory, Center for Cancer Research, National Cancer Institute, National Institutes of Health, Bethesda, MD, USA.

Abstract

The peer review system is straining under rising submissions, growing manuscript complexity, and a shrinking reviewer pool. Meanwhile an increasing number of researchers now use tools based on large language models (LLMs) when performing peer review, often without disclosure and against journal policies. This erodes trust in peer review and risks deteriorating the quality and integrity of research publications. We argue for professionalization and transparency rather than prohibition, and propose guidelines built on three aspects: model selection and data protection, human guidance and accountability, and publication integrity. These principles offer a sustainable path forward, leaving scientific judgment where it belongs; that is, with human experts.

Related

  1. Explainable artificial intelligence (XAI) in schizophrenia: enhancing transparency in clinical decision-making
    Kshitij Srivastava, Ruby Srivastava
    Frontiers in systems biologyPeer-reviewedCC BYFull textMolecular biology & gene regulationEurope PMC
  2. Adherens Junctions and Spectrin-Associated Proteins Function Interdependently to Stabilize Fiber Cell Membranes and Preserve Lens Transparency
    Electra Coffman, Jessica B. Martin, Timothy F. Plageman
    Investigative Ophthalmology & Visual SciencePeer-reviewedCC BY-NC-ND 4.0Full textMolecular biology & gene regulationPMC
  3. Antagonistic DNA methylation dynamics at a single locus controls pollen tube guidance in Arabidopsis
    Daniel Bouyer, Laëtitia de Faria, Fiamma Bunello +8
    Nature PortfolioPreprintCC BYFull textMolecular biology & gene regulationHAL
  4. The Cxcl14 chemokine defines pioneer axon guidance and early circuit assembly in the inner ear.
    Mireia Rumbo, Aitor Bañón, Alex V Nechiporuk +1
    The Journal of cell biologyPeer-reviewedCC BYFull textGeneral biochemistryEurope PMCPMC
  5. Contactless continuous guidance of matter in its main states using curved elongated Bessel-like acoustic fields
    Dmitrii Nikolaev, Denys Iablonskyi, Alexander Martinez-Marchese +6
    Proceedings of the National Academy of Sciences of the United States of AmericaPeer-reviewedCC BY 4.0Full textMolecular biology & gene regulationPMC
BibTeX
@article{day2026tool,
  title = {{LLM tool use in manuscript review: Toward guidance and transparency.}},
  author = {Chi-Ping Day and Besa Xhabija and Vishaka Gopalan},
  journal = {Life science alliance},
  year = {2026},
  month = nov,
  doi = {10.26508/lsa.202603913},
  url = {https://europepmc.org/article/MED/43009281},
  note = {CC BY},
}
RIS
TY  - JOUR
TI  - LLM tool use in manuscript review: Toward guidance and transparency.
AU  - Chi-Ping Day
AU  - Besa Xhabija
AU  - Vishaka Gopalan
PY  - 2026
DA  - 2026/11/10
JO  - Life science alliance
DO  - 10.26508/lsa.202603913
UR  - https://europepmc.org/article/MED/43009281
AB  - The peer review system is straining under rising submissions, growing manuscript complexity, and a shrinking reviewer pool. Meanwhile an increasing number of researchers now use tools based on large language models (LLMs) when performing peer review, often without disclosure and against journal policies. This erodes trust in peer review and risks deteriorating the quality and integrity of research publications. We argue for professionalization and transparency rather than prohibition, and propose guidelines built on three aspects: model selection and data protection, human guidance and accountability, and publication integrity. These principles offer a sustainable path forward, leaving scientific judgment where it belongs; that is, with human experts.
SN  - 2575-1077
ER  -