Can LLMs Normalize Databases? A Benchmark and Multi-Agent Framework for Schema Normalization
A Database Normalization Benchmark (DNBENCH), comprising 3,275 samples for evaluating LLM-driven database normalization from 1NF to BCNF, and proposes Multi-Agent Reasoning for Schemas (MARS), which separates evidence extraction, violation diagnosis, and decomposition planning from schema generation and verification.
Dong-Jae Koh, Huisu Kim, Seonghwan Yoon et al.
· 0 citations