CheckSupport: A Local LLM-Powered Tool for Automated Manuscript Submission Checklist Selection and Completion
Satvik Tripathi, Don Enwerem, Kevin Song, Kristian Quevada, Jacinta Arnold, Tessa S. Cook

TL;DR
CheckSupport is a locally deployable LLM-based tool that automates manuscript reporting checklist recommendations and completions, enhancing transparency and reproducibility in scientific research.
Contribution
It introduces a staged prompting approach for local LLM inference, achieving high accuracy in checklist automation without compromising data privacy.
Findings
90% accuracy in checklist recommendations
88% accuracy in checklist item completion
12.5 seconds average processing time per manuscript
Abstract
Transparent and standardized reporting is essential for reproducible scientific research, yet adherence to reporting guidelines remains inconsistent because of the manual effort required to select and complete checklists. We present CheckSupport, an open-source, locally deployable system that uses large language models to automate the recommendation of reporting checklists and the evidence-grounded completion of checklists for scientific manuscripts. CheckSupport employs a staged prompting strategy that decomposes reporting workflows into constrained inference tasks, prioritizing faithful extraction over generative text synthesis. All inference is performed locally using instruction-tuned models, preserving data privacy and enabling reproducible, auditable workflows. Evaluated on a corpus of peer-reviewed manuscripts, CheckSupport achieved 90% overall accuracy for checklist…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
