Metraipolis › archive › dc_bf328bd00e51
Schema-Free Text-to-SQL: Learning Enterprise Database Structure from Query Logs — arXiv:2610.33946
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.33946
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-27T08:11:28.838Z
- SHA-256 of the archived text
9f2c164c26108c1462ddbfb74ecbb0ceeb1d7e4c7601870be6caea27c821dc0e- Stable URL of this page
https://metraipolis.com/documento/dc_bf328bd00e51
How to cite
Schema-Free Text-to-SQL: Learning Enterprise Database Structure from Query Logs — arXiv:2610.33946 — arXiv (en), https://arxiv.org/abs/2610.33946 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bf328bd00e51 (Metraipolis archive dc_bf328bd00e51, sha256 9f2c164c26108c1462ddbfb74ecbb0ceeb1d7e4c7601870be6caea27c821dc0e)
BibTeX
@misc{dcbf328bd00e51,
title = {Schema-Free Text-to-SQL: Learning Enterprise Database Structure from Query Logs — arXiv:2610.33946},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.33946},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bf328bd00e51; sha256 9f2c164c26108c1462ddbfb74ecbb0ceeb1d7e4c7601870be6caea27c821dc0e},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.33946. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Text-to-SQL systems achieve remarkable accuracy on academic benchmarks, yet performance drops dramatically in enterprise deployments. This gap stems from a fundamental assumption: existing approaches require complete schema documentation, but enterprise databases typically lack comprehensive documentation, featuring cryptic naming and implicit relationships. We present the first text-to-SQL framework that operates without schema documentation, instead learning database structure from historical query logs. Query logs encode implicit structural knowledge: which tables are queried together, how they join, and what columns map to business concepts. We construct a knowledge graph from parsed query patterns and introduce entity-driven GraphRAG retrieval that grounds user questions in domain terminology rather than relying solely on embedding similarity. Validated on both an industrial deployment with expert evaluation and the Beaver benchmark, our approach substantially outperforms similarity-based retrieval methods, the dominant industry approach, in both executability and answer quality. On Beaver, we achieve 95.7% execution validity compared to 60.8% for embedding-based retrieval, with expert data engineers preferring our system 70% to 10% on internal deployment. Our work demonstrates that text-to-SQL can operate effectively in schema-ambiguous enterprise environments, enabling natural language database interfaces "in the wild". Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno). Categorie arXiv: Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2610.33946 — 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 2026-10-27T07:56:00.215Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).