Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Wang, Sha, Li, Yuchen, Xiao, Hanhua, Dai, Bing Tian, Lee, Roy Ka-Wei, Dong, Yanfei, Deng, Lambert
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2507.10897
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866913941160984576
author Wang, Sha
Li, Yuchen
Xiao, Hanhua
Dai, Bing Tian
Lee, Roy Ka-Wei
Dong, Yanfei
Deng, Lambert
author_facet Wang, Sha
Li, Yuchen
Xiao, Hanhua
Dai, Bing Tian
Lee, Roy Ka-Wei
Dong, Yanfei
Deng, Lambert
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2507_10897
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle LLMATCH: A Unified Schema Matching Framework with Large Language Models
Wang, Sha
Li, Yuchen
Xiao, Hanhua
Dai, Bing Tian
Lee, Roy Ka-Wei
Dong, Yanfei
Deng, Lambert
Databases
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.
title LLMATCH: A Unified Schema Matching Framework with Large Language Models
topic Databases
url https://arxiv.org/abs/2507.10897