# SINT-Flow: Schema Integration using Large Language Model Workflows

arXiv: https://arxiv.org/abs/2607.24492 · HTML: https://mlsanity.com/paper/2607.24492/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 39 references that are in the map.
- First posted on arXiv 27 Jul 2026.

## Builds on (most cited first, 6 of 6)

- [Language Models Enable Simple Systems for Generating Structured Views of Heterogeneous Data Lakes](https://mlsanity.com/paper/2304.09433/) (2023)
- [LLMs4OL: Large Language Models for Ontology Learning](https://mlsanity.com/paper/2307.16648/) (2023)
- [Valentine: Evaluating Matching Techniques for Dataset Discovery](https://mlsanity.com/paper/2010.07386/) (2020)
- [Mind the Data Gap: Bridging LLMs to Enterprise Data Integration](https://mlsanity.com/paper/2412.20331/) (2024)
- [Retrieval-Augmented Generation of Ontologies from Relational Databases](https://mlsanity.com/paper/2506.01232/) (2025)
- [Table Integration in Data Lakes Unleashed: Pairwise Integrability Judgment, Integrable Set Discovery, and Multi-Tuple Conflict Resolution](https://mlsanity.com/paper/2412.00324/) (2024)

## Built on by (most cited first, 1 of 1)

- [Label Agreement Does Not Measure Authorization](https://mlsanity.com/paper/2610.04544/) (2026)

## Abstract (arXiv)

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.