Exploring LLM Capabilities in Extracting DCAT-Compatible Metadata for Data Cataloging

Lennart Busch, Daniel Tebernum, Gissel Velarde

2025

Abstract

Efficient data exploration is crucial as data becomes increasingly important for accelerating processes, improving forecasts and developing new business models. Data consumers often spend 25-98% of their time searching for suitable data due to the exponential growth, heterogeneity and distribution of data. Data catalogs can support and accelerate data exploration by using metadata to answer user queries. However, as metadata creation and maintenance is often a manual process, it is time-consuming and requires expertise. This study investigates whether LLMs can automate metadata maintenance of text-based data and generate high-quality DCAT-compatible metadata. We tested zero-shot and few-shot prompting strategies with LLMs from different vendors for generating metadata such as titles and keywords, along with a fine-tuned model for classification. Our results show that LLMs can generate metadata comparable to human-created content, particularly on tasks that require advanced semantic understanding. Larger models outperformed smaller ones, and fine-tuning significantly improves classification accuracy, while few-shot prompting yields better results in most cases. Although LLMs offer a faster and reliable way to create metadata, a successful application requires careful consideration of task-specific criteria and domain context.

Paper Citation

in Harvard Style

Busch L., Tebernum D. and Velarde G. (2025). Exploring LLM Capabilities in Extracting DCAT-Compatible Metadata for Data Cataloging. In Proceedings of the 14th International Conference on Data Science, Technology and Applications - Volume 1: DATA; ISBN 978-989-758-758-0, SciTePress, pages 299-309. DOI: 10.5220/0013458500003967

in Bibtex Style

@conference{data25,
author={Lennart Busch and Daniel Tebernum and Gissel Velarde},
title={Exploring LLM Capabilities in Extracting DCAT-Compatible Metadata for Data Cataloging},
booktitle={Proceedings of the 14th International Conference on Data Science, Technology and Applications - Volume 1: DATA},
year={2025},
pages={299-309},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013458500003967},
isbn={978-989-758-758-0},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 14th International Conference on Data Science, Technology and Applications - Volume 1: DATA
TI - Exploring LLM Capabilities in Extracting DCAT-Compatible Metadata for Data Cataloging
SN - 978-989-758-758-0
AU - Busch L.
AU - Tebernum D.
AU - Velarde G.
PY - 2025
SP - 299
EP - 309
DO - 10.5220/0013458500003967
PB - SciTePress