Retrieval-Augmented Generation of Ontologies from Relational Databases
This addresses the challenge of semantic interoperability and graph-based learning for data engineers and researchers, representing a novel method rather than an incremental improvement.
The paper tackles the problem of transforming relational databases into knowledge graphs with enriched ontologies, presenting RIGOR, an LLM-driven approach that automatically generates rich OWL ontologies from database schemas with minimal human effort, achieving high scores on standard quality dimensions like accuracy and completeness.
Transforming relational databases into knowledge graphs with enriched ontologies enhances semantic interoperability and unlocks advanced graph-based learning and reasoning over data. However, previous approaches either demand significant manual effort to derive an ontology from a database schema or produce only a basic ontology. We present RIGOR, Retrieval-augmented Iterative Generation of RDB Ontologies, an LLM-driven approach that turns relational schemas into rich OWL ontologies with minimal human effort. RIGOR combines three sources via RAG, the database schema and its documentation, a repository of domain ontologies, and a growing core ontology, to prompt a generative LLM for producing successive, provenance-tagged delta ontology fragments. Each fragment is refined by a judge-LLM before being merged into the core ontology, and the process iterates table-by-table following foreign key constraints until coverage is complete. Applied to real-world databases, our approach outputs ontologies that score highly on standard quality dimensions such as accuracy, completeness, conciseness, adaptability, clarity, and consistency, while substantially reducing manual effort.