Exploring LLM Capabilities in Extracting DCAT-Compatible Metadata for Data Cataloging
This addresses the time-consuming and expertise-intensive process of metadata maintenance for data consumers, offering a faster and reliable automation solution, though it is incremental as it builds on existing LLM capabilities for a specific domain.
The study tackled the problem of manual metadata creation for data catalogs by testing whether LLMs can automate the generation of DCAT-compatible metadata from text-based data, finding that LLMs produce metadata comparable to human-created content, with larger models and few-shot prompting performing better and fine-tuning improving classification accuracy.
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.