探索LLM在提取用于数据目录化的DCAT兼容元数据方面的能力
Exploring LLM Capabilities in Extracting DCAT-Compatible Metadata for Data Cataloging
- IU International University of Applied Sciences（国际应用科学大学）
- Fraunhofer Institute for Software and Systems Engineering（弗劳恩霍夫软件与系统工程研究所）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本研究探讨利用LLMs自动化生成DCAT兼容元数据以加速数据目录化，通过测试零样本、少样本提示及微调策略，发现LLMs能生成媲美人工的元数据，微调提升分类准确率，少样本提示效果更佳。
AI中文摘要：
随着数据对加速流程、改进预测和开发新业务模型变得越来越重要，高效的数据探索至关重要。由于数据的指数级增长、异构性和分布性，数据消费者通常花费25-98%的时间寻找合适的数据。数据目录可以通过使用元数据回答用户查询来支持和加速数据探索。然而，由于元数据的创建和维护通常是一个手动过程，它既耗时又需要专业知识。本研究调查了LLMs是否能够自动化基于文本数据的元数据维护，并生成高质量的DCAT兼容元数据。我们测试了来自不同供应商的LLMs的零样本和少样本提示策略，用于生成标题和关键词等元数据，并使用一个微调模型进行分类。我们的结果表明，LLMs可以生成与人类创建内容相当的元数据，特别是在需要高级语义理解的任务上。较大的模型优于较小的模型，微调显著提高了分类准确性，而少样本提示在大多数情况下产生更好的结果。尽管LLMs提供了一种更快、更可靠的创建元数据的方式，但成功的应用需要仔细考虑任务特定标准和领域上下文。
英文摘要：
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.
