A Multi-Agent System for Semantic Mapping of Relational Data to Knowledge Graphs

TL;DR

This paper introduces a multi-agent system utilizing large language models to semantically map and integrate relational databases into knowledge graphs, improving data interoperability across enterprise systems.

Contribution

It presents a novel multi-agent framework that leverages LLMs for semantic mapping of relational data to knowledge graphs, achieving high accuracy and facilitating data integration.

Findings

Mapping accuracy exceeds 90% across multiple domains.

The system effectively connects structured data using existing vocabularies.

Semantic layer enhances data interoperability in enterprise environments.

Abstract

Enterprises often maintain multiple databases for storing critical business data in siloed systems, resulting in inefficiencies and challenges with data interoperability. A key to overcoming these challenges lies in integrating disparate data sources, enabling businesses to unlock the full potential of their data. Our work presents a novel approach for integrating multiple databases using knowledge graphs, focusing on the application of large language models as semantic agents for mapping and connecting structured data across systems by leveraging existing vocabularies. The proposed methodology introduces a semantic layer above tables in relational databases, utilizing a system comprising multiple LLM agents that map tables and columns to Schema.org terms. Our approach achieves a mapping accuracy of over 90% in multiple domains.