Taming the AI Curator: A Content Focused Data Description Diagnostic and Assistive Writing Tool
We designed an AI based tool to diagnose and help users write clear, accurate, and complete data descriptions. The tool's components include best practices data description guidelines, data descriptions reviewed by experts as few-shot prompts, and chain of thought reasoning to explain the diagnostic outputs. We engineered our prompts and Large Language Model choice so that a score of 8 reflects an acceptable data description. Users can double check the evaluations and the assisted descriptions to minimize scores inconsistent with expert reviewers and hallucinated outputs. The application is crafted to match the standards of our field and to be used with guided intention.
Authors
- Gabriel R. Jaffe (ORCID: https://orcid.org/0000-0003-2672-0375)
- M. A. Hanlon
- Bernard Chang
- Masa Prodanovic
- Zachary Nowacek
Institutions
- Washington University in St. Louis (US)
- The University of Texas at Austin (US)
Publication Details
- Journal
- Zenodo (CERN European Organization for Nuclear Research)
- Published
- 2026-02-17
- DOI
- https://doi.org/10.5281/zenodo.18803940
- Primary Topic
- Data Visualization and Analytics
- Type
- article
- Field-Weighted Citation Impact
- 0.00