Metraipolis › archive › dc_66ca4e402bd0

VCoT-SQL: Enhancing Text-to-SQL Generation through Dual Chain-of-Thought Validation Training — arXiv:2611.00815

Source: arXiv (en)
Original: https://arxiv.org/abs/2611.00815
License (as archived): CC0-1.0
Archived: 2026-11-03T18:12:14.798Z
SHA-256 of the archived text: f5cc6f58fd32ee32fdad9dfc4e60eef050812e656326134233c66aa53e4d091d
Stable URL of this page: https://metraipolis.com/documento/dc_66ca4e402bd0

How to cite

VCoT-SQL: Enhancing Text-to-SQL Generation through Dual Chain-of-Thought Validation Training — arXiv:2611.00815 — arXiv (en), https://arxiv.org/abs/2611.00815 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_66ca4e402bd0 (Metraipolis archive dc_66ca4e402bd0, sha256 f5cc6f58fd32ee32fdad9dfc4e60eef050812e656326134233c66aa53e4d091d)

BibTeX

@misc{dc66ca4e402bd0,
  title = {VCoT-SQL: Enhancing Text-to-SQL Generation through Dual Chain-of-Thought Validation Training — arXiv:2611.00815},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.00815},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_66ca4e402bd0; sha256 f5cc6f58fd32ee32fdad9dfc4e60eef050812e656326134233c66aa53e4d091d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.00815. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Open-source LLMs provide a flexible alternative to closed-source models for Text-to-SQL but still struggle with complex queries. Finetuning with chain-of-thought (CoT) data improves reasoning, yet standard datasets lack CoT annotations, requiring synthetic generation. Existing synthesis methods only verify the final answer, allowing flawed reasoning steps to corrupt the training data. We propose VCoT-SQL, a framework that improves Text-to-SQL generation through intermediate-step validated CoT supervision and a dedicated SQL validator, which enables small open-source models to outperform frontier closed-source models. VCoT-SQL trains two complementary models on curated reasoning traces: an SQL generator using clause-level CoT templates where reasoning steps are verified via execution and schema alignment checks, and an SQL validator using diagnostic CoT templates to detect syntactic, semantic, and type level errors. We further design a hierarchical schema filtering pipeline that integrates and refines complementary retrieval strategies to distill relevant database elements. VCoT-SQL achieves 66.82% execution accuracy on challenging dataset BIRD dev and 86.8% on Spider test, improving the base 7B model by 7% on BIRD. Notably, our CoT synthesis relies on 7B models yet outperforms methods that use 72B-scale or even proprietary closed source teachers for data generation, demonstrating that rigorous step-level validation can be more effective than scaling up teacher model size. Our dataset and code are available at this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2611.00815 — 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 2026-11-03T18:09:53.317Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).