# LLMATCH: A Unified Schema Matching Framework with Large Language Models

arXiv: https://arxiv.org/abs/2507.10897 · HTML: https://mlsanity.com/paper/2507.10897/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Jul 2025.

## Built on by (most cited first, 2 of 2)

- [InfraGPT Smart Infrastructure: An End-to-End VLM-Based Framework for Detecting and Managing Urban Defects](https://mlsanity.com/paper/2510.16017/) (2025)
- [RACT: Retrieval Augmented Column-Table Learning and Prediction for Multi-Table Schema Matching](https://mlsanity.com/paper/2606.07843/) (2026)

## Abstract (arXiv)

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.