SINT-Flow

SINT-Flow: LLM workflow framework for automated schema integration with new SINT-Bench benchmark

SINT-Flow is a schema integration framework using five LLM-based operators composed into workflows to perform fully automated end-to-end schema integration, including decomposition of denormalized tables describing multiple entity types. The authors also introduce SINT-Bench, a benchmark of 10 schema integration tasks across 93 relational tables. Evaluation using GPT-5.2 and Qwen-3.6-27B as backbone models achieves F1 scores of 96%+ for entity-type detection, 85% for attribute detection, and 83% for schema mapping. The work demonstrates LLM applicability to a classical database integration problem with a self-consistency strategy and review loop ablation.