arXiv cs.CL· Keti Korini, Christian Bizer·· 12 小时前AI 评分31
SINT-Flow：用大语言模型工作流实现 Schema 集成
SINT-Flow: Schema Integration using Large Language Model Workflows
AI 导读
SINT-Flow 是一个由五个 LLM 算子组合成工作流的 schema 集成框架，可全自动端到端处理含多实体类型的反规范化源表，并将其拆分为实体专属关系。
正文 · 原文
Abstract: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 a Completeness rate of at least 97% in entity type detection, 81% for attribute detection, and an F1-score of 84% 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.
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2607.24492 [cs.CL] |
| (or arXiv:2607.24492v2 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2607.24492 arXiv-issued DOI via DataCite |
Submission history
From: Keti Korini [view email]
[v1]
Mon, 27 Jul 2026 14:28:17 UTC (2,172 KB)
[v2]
Tue, 20 Oct 2026 14:28:08 UTC (2,059 KB)
来源：arXiv cs.CL · arxiv.org