LLMATCH: A Unified Schema Matching Framework with Large Language Models

TL;DR

This paper introduces LLMatch, a modular schema matching framework leveraging large language models, which improves accuracy and efficiency in complex multi-table data integration tasks.

Contribution

The paper presents LLMatch, a novel, unified schema matching framework with a two-stage optimization strategy and introduces SchemaNet, a new benchmark for complex schema matching evaluation.

Findings

LLMatch significantly improves matching accuracy in complex scenarios.

LLMatch boosts engineer productivity in real-world data integration.

SchemaNet effectively captures multi-table schema matching challenges.

Abstract

Schema matching is a foundational task in enterprise data integration, aiming to align disparate data sources. While traditional methods handle simple one-to-one table mappings, they often struggle with complex multi-table schema matching in real-world applications. We present LLMatch, a unified and modular schema matching framework. LLMatch decomposes schema matching into three distinct stages: schema preparation, table-candidate selection, and column-level alignment, enabling component-level evaluation and future-proof compatibility. It includes a novel two-stage optimization strategy: a Rollup module that consolidates semantically related columns into higher-order concepts, followed by a Drilldown module that re-expands these concepts for fine-grained column mapping. To address the scarcity of complex semantic matching benchmarks, we introduce SchemaNet, a benchmark derived from real-world schema pairs across three enterprise domains, designed to capture the challenges of multi-table schema alignment in practical settings. Experiments demonstrate that LLMatch significantly improves matching accuracy in complex schema matching settings and substantially boosts engineer productivity in real-world data integration.