Conceptual Schema Inference for Tabular Datasets using Large Language Models
For data management practitioners dealing with heterogeneous tabular data repositories, this work addresses the underexplored problem of automatically inferring conceptual schemas, though the novelty is incremental as it applies existing LLM techniques to a known bottleneck.
This paper tackles conceptual schema inference from raw tabular datasets, proposing two LLM-based approaches (GeSI and EmSI) that automatically derive entity types, attributes, and relationships. Experimental results show effectiveness in conciseness, structural quality, and scalability to large repositories.
Large collections of tabular data from data lakes, web tables and open data portals often originate from heterogeneous sources, leading to representational inconsistencies. Understanding and organizing such repositories therefore remains a major challenge. While prior work has primarily focused on dataset discovery and exploration, this paper addresses the complementary problem of conceptual schema inference: automatically deriving a conceptual schema that captures entity types, attributes and inter-type relationships directly from raw tables. We propose two large language model (LLM)-based approaches that use only column headers and cell values: GeSI uses generative LLMs to infer hierarchical types and their attributes from table- and column-level semantics, and to integrate them into a global schema that also captures relationships across types; EmSI employs LLM-based table embeddings to group tables by column-level semantics, infer attributes within each group, and construct hierarchical structures from shared attribute patterns. Finally, we report an experimental analysis demonstrating the effectiveness of our approaches in terms of the conciseness and structural quality of the inferred schema components, their scalability to large repositories, and a case study illustrating end-to-end schema inference.