Metraipolis › archive › dc_15e9869bde20

Closing the Cross-Dialect Gap: Query Plans as a Portable Interface in Text-to-SQL — arXiv:2609.33670

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.33670
License (as archived)
CC0-1.0
Archived
2026-10-07T21:53:06.799Z
SHA-256 of the archived text
838975723eda982d9fa4cc716542959672217a6ddd03ad3d3fb35c67de3f7ea1
Stable URL of this page
https://metraipolis.com/documento/dc_15e9869bde20

How to cite

Closing the Cross-Dialect Gap: Query Plans as a Portable Interface in Text-to-SQL — arXiv:2609.33670 — arXiv (en), https://arxiv.org/abs/2609.33670 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_15e9869bde20 (Metraipolis archive dc_15e9869bde20, sha256 838975723eda982d9fa4cc716542959672217a6ddd03ad3d3fb35c67de3f7ea1)
BibTeX
@misc{dc15e9869bde20,
  title = {Closing the Cross-Dialect Gap: Query Plans as a Portable Interface in Text-to-SQL — arXiv:2609.33670},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.33670},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_15e9869bde20; sha256 838975723eda982d9fa4cc716542959672217a6ddd03ad3d3fb35c67de3f7ea1},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.33670. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Text-to-SQL systems are typically trained and evaluated on a single dialect (SQLite), yet production deployments span PostgreSQL, MySQL, ClickHouse, and beyond. We show that this single-dialect assumption leads to a substantial drop in cross-dialect accuracy for every model we tested. The drop persists across scale, architecture, and even purpose-built text-to-SQL systems. We argue that the fix is to change the generation target: instead of asking an LLM to emit dialect-specific SQL, we have it emit a dialect-agnostic relational algebra query plan, which a deterministic compiler then renders into SQL for any supported backend. Across thirteen models from 3B to frontier scale, this restores cross-dialect portability nearly uniformly, at a small cost in peak accuracy on the model's home dialect for capable prompted models and none once fine-tuned on plans; under matched fine-tuning, plan supervision yields a stronger model than SQL supervision. We also introduce MetricName, a question-aware result-set comparator needed to evaluate fairly across dialects, where existing metrics confound semantic errors with benign cross-dialect variation. More broadly, the result is a reminder that a generation target chosen for execution is not necessarily the one that maximizes generation quality.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2609.33670 — 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 2026-10-07T21:27:08.539Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).