Can LLMs Normalize Databases? A Benchmark and Multi-Agent Framework for Schema Normalization

Excerpt

arXiv:2609.11141v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly used to generate structured outputs, but their reliability remains unclear when those outputs must satisfy database-level constraints. We study this issue through database normalization, involving reasoning about functional dependencies, lossless join decompositions, and inter-table constraints. We introduce a Database Normalization Benchmark (DNBENCH), comprising 3,275 samples for evaluating LLM-driven