Column matching is a central task in reconciling schemas for data integration. Column names and descriptions are valuable for this task. LLMs can leverage such natural-language schema metadata. However, in many datasets, correct matching requires additional evidence beyond the column itself. Because it is impractical to provide an LLM with the entire schema metadata needed to capture this evidence, the core challenge becomes to select and organize the most useful contextual information. We present ConStruM, a structure-guided framework for budgeted evidence packing in schema matching. ConStruM constructs a lightweight, reusable structure in which, at query time, it assembles a small context pack emphasizing the most discriminative evidence. ConStruM is designed as an add-on: given a shortlist of candidate targets produced by an upstream matcher, it augments the matcher's final LLM prompt with structured, query-specific evidence so that the final selection is better grounded. For this purpose, we develop a context tree for budgeted multi-level context retrieval and a global similarity hypergraph that surfaces groups of highly similar columns (on both the source and target sides), summarized via group-aware differentiation cues computed online or precomputed offline. Experiments on real datasets show that ConStruM improves matching by providing and organizing the right contextual evidence.

翻译：列匹配是数据集成中协调模式的核心任务。列名和列描述对此任务具有重要价值。大语言模型（LLM）能够利用此类自然语言模式元数据。然而，在许多数据集中，正确的匹配需要超出列本身之外的额外证据。由于向LLM提供捕获这些证据所需的全部模式元数据是不切实际的，核心挑战便转化为如何选择和组织最有用的上下文信息。我们提出了ConStruM，一种用于模式匹配中预算化证据打包的结构引导框架。ConStruM构建了一个轻量级、可重用的结构，在查询时，该结构会组装一个强调最具区分性证据的小型上下文包。ConStruM被设计为一个附加组件：给定上游匹配器生成的候选目标短列表，它用结构化、查询特定的证据来增强匹配器的最终LLM提示，从而使最终选择更具依据。为此，我们开发了一种用于预算化多级上下文检索的上下文树，以及一个全局相似度超图，该超图能呈现高度相似列（在源端和目标端）的群组，并通过在线计算或离线预计算的群组感知区分线索进行总结。在真实数据集上的实验表明，ConStruM通过提供并组织恰当的上下文证据，有效提升了匹配性能。