Searcharxiv⌕ Search

arXiv · 2611.14648

Evaluating the Performance of LLMs in Drafting NIH Data Management Plans

Abstract

Sharing research data is essential to promote transparency, enable reproducibility, and fuel scientific discoveries. To ensure consistent sharing, the National Institutes of Health (NIH) and other funding agencies require applicants to submit data management plans (DMPs) with their proposals. They aim to encourage researchers to consider their data management and sharing strategies early on. However, researchers often face challenges when developing DMPs due to a lack of knowledge about data-sharing practices. Here, we evaluated the performance of Large Language Models (LLMs) in drafting DMPs compliant with the 2023 NIH guidelines. The goal was to investigate whether LLM-supported DMP creation could reduce the burden on researchers and librarians. We compared Llama and GPT performance against NIH-provided DMP samples. We also asked domain experts to evaluate LLM-generated DMPs. Overall, we found that LLMs can accelerate the creation of initial drafts but still require expert review before submission to ensure clarity and completeness. Moreover, open-source LLMs may not be as ready off-the-shelf as commercial ones for drafting funder-compliant DMPs.

Explore related subjects

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Nahid Zeinali, James ONeil, Xuebin Dong, Rebecca Hofstein Grady, Maria Praetzellis, Brian Riley, John Chodacki, Bhavesh Patel. 2026-11-10. Evaluating the Performance of LLMs in Drafting NIH Data Management Plans. https://searcharxiv.com/abs/2611.14648

Citations retain the original authors and DOI and include this site’s record URL. If this discovery service contributed to your research, you can also cite Searcharxiv by Indiciae: BibTeX · RIS.

KEEP EXPLORING

Related papers

Where Do Highly Cited Scientists Stand? A Multi-Dimensional Analysis of Positional Distribution in the Top 2% Ranking

The Top 2% Scientists list is widely used. Yet current applications either only count the number of scientists in different units or criticize the list's validity as a measure of individual impact. We introduce positional enrichment, a scale-free framework that compares observed to expected counts across percentile bins on the list, revealing where a unit's scientists tend to sit along the list rather than how many it contributes. Applying positional enrichment to the 2026 single-year list, we show that countries, institutions, and research subfields each fall into a consistent pattern of three groups with Head-, Middle-, and Tail-enriched profiles. Subfield profiles are globally stable, whereas countries and institutions are heterogeneous across subfields. National and institutional differences are therefore compositional. Therefore, the reason of a country or institution sitting near the head of the list is unlikely its scientists performing better within the same subfields, while it holding more of the subfields that sit near the head. Academic age adds an independent dimension, with stronger enrichment toward the head after 25 years and exceptions in fast-moving subfields such as artificial intelligence. We show the ranking is not a flat ordering of individual influence but a subfield-organized stratification.

cs.DL↗

Have Large Language Models Enhanced the Way Civil & Environmental Engineers Write? A Quantitative Analysis of Scholarly Communication over 25 Years

Large language models (LLMs) have rapidly emerged in civil and environmental engineering (CEE) research, education, and practice as tools for project ideation, execution, and communication. However, a gap remains in understanding how prevalent LLM adoption is across CEE scholarship and whether it measurably alters research prose. This study applies a vocabulary-based frequency-shift methodology to 149,452 abstracts published by the American Society of Civil Engineers between 2000 and 2025. Deviations from long-term vocabulary trends suggest that 15.3% and 26.9% of 2024 and 2025 abstracts, respectively, are likely LLM-influenced. Prior to the introduction of LLMs in 2022, CEE publications exhibit long-term trends toward longer abstracts, greater use of segmenting punctuation, higher required reading levels, and use of active, first-person verb constructions. Beginning around 2023, however, the frequencies of many stylistic marker words (e.g., enhance) sharply depart from their historical trajectories, a shift consistent with the emergence of LLMs. Abstracts classified as likely LLM-influenced also depart from historical semantic trends, exhibiting increased lexical diversity, comma use, and complexity, with reduced passive voice and hedging language, producing prose that is more segmented, complex, and confident. The artificial intelligence contribution of this study is the use of natural language processing to detect population-level linguistic signals of LLM-generated text, estimating the prevalence of LLM use and its influence on CEE writing. Together, these novel findings provide the first large-scale, data-driven assessment of how CEE scholarly communication is changing alongside LLM adoption.

cs.DL↗

Comparison of OpenAlex and Scopus coverage of German institutions' publications in top-tier journals

OpenAlex has recently emerged as a leading alternative to proprietary bibliometric sources. However, concerns remain regarding the quality of its metadata, especially the institutional profiles which are crucial for evaluating organizations. This study assesses the quality of affiliation data in OpenAlex using German research institutions. Publications from top-tier journals were analyzed and institutional publication counts in OpenAlex were systematically compared with counts in Scopus. The results show that OpenAlex generally contains more publications at the journal level, reflecting its broader coverage. However, institutional publication counts in OpenAlex are consistently lower; it contained 6.8% fewer institution-paper links in the analyzed sample. Aggregate institutional counts nevertheless showed very high rank correlation and concordance with Scopus. Discrepancies varied substantially across fields, publishers and journals. Detailed investigation identified missing affiliation information, differences in institutional boundaries, and divergent year and journal assignments, while errors present in both databases. These findings suggest that OpenAlex is suitable for comparative institutional analyses in academic research but requires further improvement in affiliation metadata before it can be used for evaluation contexts that rely on absolute publication counts.

cs.DL↗