Metraipolis › archive › dc_bd13a09501ad

Can LLMs Normalize Databases? A Benchmark and Multi-Agent Framework for Schema Normalization — arXiv:2609.11141

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.11141
License (as archived)
CC0-1.0
Archived
2026-10-16T05:44:05.161Z
SHA-256 of the archived text
0944526ebbcf2da30efc1edb46ec3fe6e2b8bf489d25a3b58600cad7170d9e9c
Stable URL of this page
https://metraipolis.com/documento/dc_bd13a09501ad

How to cite

Can LLMs Normalize Databases? A Benchmark and Multi-Agent Framework for Schema Normalization — arXiv:2609.11141 — arXiv (en), https://arxiv.org/abs/2609.11141 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bd13a09501ad (Metraipolis archive dc_bd13a09501ad, sha256 0944526ebbcf2da30efc1edb46ec3fe6e2b8bf489d25a3b58600cad7170d9e9c)
BibTeX
@misc{dcbd13a09501ad,
  title = {Can LLMs Normalize Databases? A Benchmark and Multi-Agent Framework for Schema Normalization — arXiv:2609.11141},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.11141},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bd13a09501ad; sha256 0944526ebbcf2da30efc1edb46ec3fe6e2b8bf489d25a3b58600cad7170d9e9c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.11141. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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 database normalization from 1NF to BCNF. DNBENCH uses a three-axis protocol to measure semantic equivalence, structural accuracy, and logical validity. Across Single, Complex, and Real World levels, DNBENCH uncovers recurring failures in dependency inference, schema decomposition, and inter-table constraint reconstruction. We further propose Multi-Agent Reasoning for Schemas (MARS), which separates evidence extraction, violation diagnosis, and decomposition planning from schema generation and verification. MARS improves the DNB-SCORE by 82.0% over the single-prompt baseline. All artifacts will be released upon acceptance.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-11 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2609.11141 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-16T05:23:57.002Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).