Metraipolis › archive › dc_8564a2f5cf2f

NL2SQL with Iterative Self-Refinement — arXiv:2610.22968

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.22968
License (as archived): CC0-1.0
Archived: 2026-10-19T08:43:04.806Z
SHA-256 of the archived text: ca1021cc1ba7b3a88f8b39ea76f36f78e1cc2af1505d4ab0ea228aa311f6b53e
Stable URL of this page: https://metraipolis.com/documento/dc_8564a2f5cf2f

How to cite

NL2SQL with Iterative Self-Refinement — arXiv:2610.22968 — arXiv (en), https://arxiv.org/abs/2610.22968 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8564a2f5cf2f (Metraipolis archive dc_8564a2f5cf2f, sha256 ca1021cc1ba7b3a88f8b39ea76f36f78e1cc2af1505d4ab0ea228aa311f6b53e)

BibTeX

@misc{dc8564a2f5cf2f,
  title = {NL2SQL with Iterative Self-Refinement — arXiv:2610.22968},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.22968},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8564a2f5cf2f; sha256 ca1021cc1ba7b3a88f8b39ea76f36f78e1cc2af1505d4ab0ea228aa311f6b53e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.22968. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Bridging the gap between human intent and machine logic remains a critical challenge in data access for non-technical users, yet Large Language Models (LLMs) remain unreliable: they hallucinate schema elements, generate syntactically invalid queries, or fail to capture user intent. These limitations are especially critical in domains such as insurance, where KPIs, regulatory constraints, and legacy relational systems demand high precision. We introduce a multi-agent, persona-driven NL2SQL framework that combines (1) domain relevance detection, (2) schema-grounded knowledge construction, (3) KPI-aware SQL synthesis, (4) syntax-level self-repair using sqlite execution feedback, and (5) semantic consistency checking via SQL-to-NL reverse engineering. Our system significantly reduces query hallucination and improves semantic fidelity compared to direct LLM prompting. Evaluated on 60 queries (50 from a HuggingFace text-to-SQL dataset and 10 custom domain queries), the system achieves 90% correctness using Mistral across seven coordinated LLM calls showing that this approach can substantially increase the reliability of NL2SQL pipelines in high-stakes environments.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Databases (cs.DB) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.22968 — 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 2026-10-19T08:39:10.136Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).