GBV-SQL: Guided Generation and SQL2Text Back-Translation Validation for Multi-Agent Text2SQL

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Chen, Daojun, Wang, Xi, Ren, Shenyuan, Ma, Qingzhi, Zhao, Pengpeng, Liu, An
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866908541014507520
author Chen, Daojun
Wang, Xi
Ren, Shenyuan
Ma, Qingzhi
Zhao, Pengpeng
Liu, An
author_facet Chen, Daojun
Wang, Xi
Ren, Shenyuan
Ma, Qingzhi
Zhao, Pengpeng
Liu, An
contents While Large Language Models have significantly advanced Text2SQL generation, a critical semantic gap persists where syntactically valid queries often misinterpret user intent. To mitigate this challenge, we propose GBV-SQL, a novel multi-agent framework that introduces Guided Generation with SQL2Text Back-translation Validation. This mechanism uses a specialized agent to translate the generated SQL back into natural language, which verifies its logical alignment with the original question. Critically, our investigation reveals that current evaluation is undermined by a systemic issue: the poor quality of the benchmarks themselves. We introduce a formal typology for "Gold Errors", which are pervasive flaws in the ground-truth data, and demonstrate how they obscure true model performance. On the challenging BIRD benchmark, GBV-SQL achieves 63.23% execution accuracy, a 5.8% absolute improvement. After removing flawed examples, GBV-SQL achieves 96.5% (dev) and 97.6% (test) execution accuracy on the Spider benchmark. Our work offers both a robust framework for semantic validation and a critical perspective on benchmark integrity, highlighting the need for more rigorous dataset curation.
format Preprint
id arxiv_https___arxiv_org_abs_2509_12612
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle GBV-SQL: Guided Generation and SQL2Text Back-Translation Validation for Multi-Agent Text2SQL
Chen, Daojun
Wang, Xi
Ren, Shenyuan
Ma, Qingzhi
Zhao, Pengpeng
Liu, An
Artificial Intelligence
While Large Language Models have significantly advanced Text2SQL generation, a critical semantic gap persists where syntactically valid queries often misinterpret user intent. To mitigate this challenge, we propose GBV-SQL, a novel multi-agent framework that introduces Guided Generation with SQL2Text Back-translation Validation. This mechanism uses a specialized agent to translate the generated SQL back into natural language, which verifies its logical alignment with the original question. Critically, our investigation reveals that current evaluation is undermined by a systemic issue: the poor quality of the benchmarks themselves. We introduce a formal typology for "Gold Errors", which are pervasive flaws in the ground-truth data, and demonstrate how they obscure true model performance. On the challenging BIRD benchmark, GBV-SQL achieves 63.23% execution accuracy, a 5.8% absolute improvement. After removing flawed examples, GBV-SQL achieves 96.5% (dev) and 97.6% (test) execution accuracy on the Spider benchmark. Our work offers both a robust framework for semantic validation and a critical perspective on benchmark integrity, highlighting the need for more rigorous dataset curation.
title GBV-SQL: Guided Generation and SQL2Text Back-Translation Validation for Multi-Agent Text2SQL
topic Artificial Intelligence
url https://arxiv.org/abs/2509.12612