SINT-Flow：使用大语言模型工作流进行模式集成
SINT-Flow: Schema Integration using Large Language Model Workflows
- University of Mannheim（曼海姆大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本文提出SINT-Flow框架，由五个基于大语言模型的算子组成工作流，用于全自动端到端模式集成，能处理非规范化源表。通过SINT-Bench基准评估，在多种任务上取得高F1分数，消融研究证明了策略和审查循环的效用。
AI中文摘要：
模式集成的目标是，给定一组输入模式或表，得出一个全局统一的模式，能够连贯地表示所有输入表中的概念、属性和关系。本文提出了SINT-Flow，一个由五个基于大语言模型的算子组成的模式集成框架，这些算子可组合成工作流以执行全自动的端到端模式集成。与现有方法不同，SINT-Flow能处理包含描述多种实体类型属性的非规范化源表，在集成过程中会将这些表分解为单独的特定实体关系。为评估SINT-Flow，引入了SINT-Bench基准，包含10个模式集成任务共93个关系表。使用GPT-5.2和开源模型Qwen-3.6-27B评估，SINT-Flow在实体类型检测、属性检测和模式映射方面分别取得至少96%、85%和83%的F1分数。还进行了消融研究以证明应用的自一致性策略和模式匹配算子中包含审查循环的效用。
英文摘要：
The goal of schema integration is, given a set of input schemata or tables, to derive a global, unified schema that is able to represent the concepts, attributes, and relationships of all input tables in a coherent fashion. This paper presents SINT-Flow, a schema integration framework composed of five LLM-based operators that can be combined into workflows to perform fully automated, end-to-end schema integration. In contrast to existing approaches, SINT-Flow can process denormalized source tables that contain attributes describing multiple entity types. During the schema integration process, these tables are decomposed into separate entity-specific relations. To evaluate SINT-Flow, we introduce SINT-Bench, a schema integration benchmark comprising 10 schema integration tasks consisting of altogether 93 relational tables, including tables that describe multiple types of entities. We evaluate SINT-Flow using GPT-5.2 as well as the open-weight model Qwen-3.6-27B as alternative backbone models. Using these models, SINT-Flow achieves F1 scores of at least 96% for entity-type detection, 85% for attribute detection, and 83% for schema mapping. Furthermore, we perform an ablation study to prove the utility of the applied self-consistency strategy as well as the inclusion of a review loop into the schema matching operator.
