AutoDDG: Automated Dataset Description Generation using Large Language Models

Abstract: The proliferation of datasets across open data portals and enterprise data lakes presents an opportunity for deriving data-driven insights. However, widely-used dataset search systems rely on keyword searches over dataset metadata, including descriptions, to facilitate discovery. When these descriptions are incomplete, missing, or inconsistent with dataset contents, findability is severely hindered. In this paper, we address the problem of automatic dataset description generation: how to generate informative descriptions that enhance dataset discovery and support relevance assessment. We introduce AutoDDG, a framework for automated dataset description generation tailored for tabular data. To derive descriptions that are comprehensive, accurate, readable and concise, AutoDDG adopts a data-driven approach to summarize the contents of a dataset, and leverages LLMs to both enrich the summaries with semantic information and to derive human-readable descriptions. An important challenge for this problem is how to evaluate the effectiveness of methods for data description generation and the quality of the descriptions. We propose a multi-pronged evaluation strategy that: (1) measures the improvement in dataset retrieval within a dataset search engine, (2) compares generated descriptions to existing ones (when available), and (3) evaluates intrinsic quality metrics such as readability, faithfulness to the data, and conciseness. Additionally, we introduce two new benchmarks to support this evaluation. Our experimental results, using these benchmarks, demonstrate that AutoDDG generates high-quality, accurate descriptions and significantly improves dataset retrieval performance across diverse use cases.