Dataset: NIH DMPs LLM Evaluation Paper

AboutData Management Plans (DMPs) are now required by most funders for grant proposals to ensure researchers plan in advance for effective data management and sharing. In this work, we evaluated the performance of Large Language Models (LLMs) in drafting DMPs compliant with the National Institutes of Health (NIH)’s 2023 guidelines. This dataset contains the data files used in our analysis of how well Llama 3.3 and GPT-4.1 can draft NIH-compliant Data Management Plans (DMPs). See this inventory for all related resources, including the paper.Standards followedThis dataset is structured according to the SPARC Data Structure v3.0.2 (see related manuscript and documentation) and curated using the SPARC data curation software SODA v17.1.0.Using the datasetSimply download this dataset. The main data files are in the primary folder. The derivative folder contains data files derived from the primary files. There is a manifest.xlsx file at the root level that describes all the files. See this inventory for the Jupyter notebook used to analyze and visualize the data.LicenseThis work is licensed under a Creative Commons Attribution 4.0 International License (see LICENSE file).How to citeIf you use this dataset, please follow the citation instructions presented on Zenodo.