Metraipolis › archive › dc_063f4561dfe4
DexterSQL: Deep Schema Exploration and Rule-based Correction for Text-to-SQL Generation — arXiv:2608.11889
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.11889
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T05:16:16.331Z
- SHA-256 of the archived text
153c89d51edd6418f5c29169b3dbce7701b5e6dddbcccae81d698f4d716e1f3d- Stable URL of this page
https://metraipolis.com/documento/dc_063f4561dfe4
How to cite
DexterSQL: Deep Schema Exploration and Rule-based Correction for Text-to-SQL Generation — arXiv:2608.11889 — arXiv (en), https://arxiv.org/abs/2608.11889 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_063f4561dfe4 (Metraipolis archive dc_063f4561dfe4, sha256 153c89d51edd6418f5c29169b3dbce7701b5e6dddbcccae81d698f4d716e1f3d)
BibTeX
@misc{dc063f4561dfe4,
title = {DexterSQL: Deep Schema Exploration and Rule-based Correction for Text-to-SQL Generation — arXiv:2608.11889},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.11889},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_063f4561dfe4; sha256 153c89d51edd6418f5c29169b3dbce7701b5e6dddbcccae81d698f4d716e1f3d},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.11889. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Prompting-based (i.e., non-fine-tuning) Text-to-SQL methods, where underlying large language model parameters are not changed for the task, face three problems: (i) relying on coarse-grained schema information that may not reveal the fine-grained relationships needed to distinguish ambiguous columns, (ii) failing to capture recurring SQL-generation failures, and (iii) suffering from omission or hallucination of components in complex questions. This paper develops DexterSQL, a prompting/non-fine-tuning-based Text-to-SQL system that improves SQL generation with three novel components: (i) deep schema explorator that identifies ambiguous columns, analyzes their individual and joint data distributions to uncover their relationships and the distinct role of each, (ii) database-agnostic rule creator that mines mismatches between generated and gold SQL only on the training database and converts them into database-agnostic corrective rules that capture recurring LLM failure patterns; and (iii) multi-path SQL generation that introduces a dependency-tree-based intermediate representation that uses the question's sentence structure to guide its decomposition into an SQL skeleton for final SQL generation. DexterSQL achieves a higher accuracy compared to the state-of-the-art using both open-source/weight and closed-source/weight models. Particularly, DexterSQL shows a high improvement of at least 5.5% using an open-weight model (GPT-OSS-120B) on BIRDDev, with total accuracy 70.4%. DexterSQL also shows better improvement of at least 1.4% using closed-weight models, with total accuracy 72.1% and 72.9% on BIRD-Dev with GPT-4o and GPT-5.2. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-13 in cs.AI). Categorie arXiv: Databases (cs.DB) ; Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Information Retrieval (cs.IR). Pagina del lavoro: https://arxiv.org/abs/2608.11889 — 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 2026-10-19T05:08:46.740Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-13?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).