Metraipolis › archive › dc_49daa2fa5de4

GRIPS: An Empirical Study of Pre-SQL Grounding Information for SQL Generation — arXiv:2611.02314

Source: arXiv (en)
Original: https://arxiv.org/abs/2611.02314
License (as archived): CC0-1.0
Archived: 2026-11-03T11:10:46.494Z
SHA-256 of the archived text: 90ea6c86a837f17f85114f6ca0908e29639560b047ff310511deb5912077a6ee
Stable URL of this page: https://metraipolis.com/documento/dc_49daa2fa5de4

How to cite

GRIPS: An Empirical Study of Pre-SQL Grounding Information for SQL Generation — arXiv:2611.02314 — arXiv (en), https://arxiv.org/abs/2611.02314 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_49daa2fa5de4 (Metraipolis archive dc_49daa2fa5de4, sha256 90ea6c86a837f17f85114f6ca0908e29639560b047ff310511deb5912077a6ee)

BibTeX

@misc{dc49daa2fa5de4,
  title = {GRIPS: An Empirical Study of Pre-SQL Grounding Information for SQL Generation — arXiv:2611.02314},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.02314},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_49daa2fa5de4; sha256 90ea6c86a837f17f85114f6ca0908e29639560b047ff310511deb5912077a6ee},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.02314. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Text-to-SQL systems answer natural language questions over structured data, but can fail before SQL generation by linking question mentions to the wrong table, column, value, or relation. Even valid SQL can then return an incorrect answer. This raises a central question: What pre-SQL information helps a SQL generator, and when does additional information cease to help? We investigate this question on TempTabQA-C and BIRD. Among the audited SQL Static failures, grounding errors form the largest category on both benchmarks. We introduce GRIPS (Grounding Representation and Input Processing for SQL generation), a three-stage method that derives structured pre-SQL information to make these decisions explicit before query generation. Across GPT-5-nano and Llama-70B, GRIPS-Adaptive improves over SQL Static in 18 of 20 settings, with an average accuracy gain of 11.8 percentage points, while reducing model-call token usage by 47.8%. Our controlled analysis shows which grounding information can improve SQL generation, whereas adding more pre-SQL information does not consistently help. By separating question-input grounding from SQL generation, GRIPS makes text-to-SQL more accurate, efficient, and easier to diagnose.

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/2611.02314 — 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 2026-11-03T10:59:52.332Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).