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

arXiv: https://arxiv.org/abs/2507.05282 · HTML: https://mlsanity.com/paper/2507.05282/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 58 references that are in the map.
- First posted on arXiv 4 Jul 2025.

## Builds on (most cited first, 17 of 17)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [A Comprehensive Overview of Large Language Models](https://mlsanity.com/paper/2307.06435/) (2023)
- [The FLORES-101 Evaluation Benchmark for Low-Resource and Multilingual Machine Translation](https://mlsanity.com/paper/2106.03193/) (2021)
- [A Discourse-Aware Attention Model for Abstractive Summarization of Long Documents](https://mlsanity.com/paper/1804.05685/) (2018)
- [LongT5: Efficient Text-To-Text Transformer for Long Sequences](https://mlsanity.com/paper/2112.07916/) (2021)
- [What Language Model Architecture and Pretraining Objective Work Best for Zero-Shot Generalization?](https://mlsanity.com/paper/2204.05832/) (2022)
- [Metrics for Multi-Class Classification: an Overview](https://mlsanity.com/paper/2008.05756/) (2020)
- [Large-Scale Multi-Label Text Classification on EU Legislation](https://mlsanity.com/paper/1906.02192/) (2019)
- [SemEval 2017 Task 10: ScienceIE - Extracting Keyphrases and Relations from Scientific Publications](https://mlsanity.com/paper/1704.02853/) (2017)
- [Is Cosine-Similarity of Embeddings Really About Similarity?](https://mlsanity.com/paper/2403.05440/) (2024)
- [PromptRank: Unsupervised Keyphrase Extraction Using Prompt](https://mlsanity.com/paper/2305.04490/) (2023)
- [Paper Abstract Writing through Editing Mechanism](https://mlsanity.com/paper/1805.06064/) (2018)
- [The W3C Data Catalog Vocabulary, Version 2: Rationale, Design Principles, and Uptake](https://mlsanity.com/paper/2303.08883/) (2023)
- [Towards Enabling FAIR Dataspaces Using Large Language Models](https://mlsanity.com/paper/2403.15451/) (2024)
- [LaFiCMIL: Rethinking Large File Classification from the Perspective of Correlated Multiple Instance Learning](https://mlsanity.com/paper/2308.01413/) (2023)

## Built on by (most cited first, 2 of 2)

- [Characterising AI Models for Cataloguing](https://mlsanity.com/paper/2607.11353/) (2026)
- [AgentFAIR: A Multi-Agent Collaborative Framework for FAIRness Evaluation of Geospatial Datasets](https://mlsanity.com/paper/2607.15781/) (2026)

## Abstract (arXiv)

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.