Exploring LLM Capabilities in Extracting DCAT-Compatible Metadata for Data Cataloging
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866918088155332608 |
|---|---|
| author | Busch, Lennart Tebernum, Daniel Velarde, Gissel |
| author_facet | Busch, Lennart Tebernum, Daniel Velarde, Gissel |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_05282 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Exploring LLM Capabilities in Extracting DCAT-Compatible Metadata for Data Cataloging Busch, Lennart Tebernum, Daniel Velarde, Gissel Information Retrieval Artificial Intelligence 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. |
| title | Exploring LLM Capabilities in Extracting DCAT-Compatible Metadata for Data Cataloging |
| topic | Information Retrieval Artificial Intelligence |
| url | https://arxiv.org/abs/2507.05282 |