Paper on LLM-based Schema Integration accepted at EDBT 2027

We are happy to announce that the paper “SINT-Flow: Schema Integration using Large Language Model Workflows” by Keti Korini and Christian Bizer was accepted as full research paper at the 30th International Conference on Extending Database Technology (EDBT2027) taking place in April 2027 in Lille, France. The paper shows that LLMs can perform end-to-end schema integration without human intervention, given that they are integrated into workflows that decompose the complex schema integration task into manageable subtasks. The paper also introduces the schema integration benchmark SINT-Bench.

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.

Arxiv Preprint: https://arxiv.org/abs/2607.24492

Github Repository: https://github.com/wbsg-uni-mannheim/SINT-Flow

Back