@inproceedings{zhang-etal-2025-high,
title = "High-Quality Complex Text-to-{SQL} Data Generation through Chain-of-Verification",
author = "Zhang, Yuchen and
Gao, Yuze and
Chen, Bin and
Li, Wenfeng and
Sun, Shuo and
Su, Jian",
editor = "Inui, Kentaro and
Sakti, Sakriani and
Wang, Haofen and
Wong, Derek F. and
Bhattacharyya, Pushpak and
Banerjee, Biplab and
Ekbal, Asif and
Chakraborty, Tanmoy and
Singh, Dhirendra Pratap",
booktitle = "Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics",
month = dec,
year = "2025",
address = "Mumbai, India",
publisher = "The Asian Federation of Natural Language Processing and The Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-ijcnlp.143/",
pages = "2368--2379",
ISBN = "979-8-89176-303-6",
abstract = "Can today{'}s Text-to-SQL benchmarks still stretch modern LLMs? We argue no. Spider1.0 and BIRD, painstakingly hand-built, remain small, costly, and skewed toward middle complex SQL. Meanwhile, LLM-generated corpora are inexpensive but often superficial and fragile suffering from shallow nesting, semantic drift, template fatigue, and insufficient quality check.We address this gap with a Chain-of-Verifications framework that turns a handful of expert-labelled seeds into a large, reliably checked dataset at a fraction of the usual cost. The resulting corpus, AIGT2S, delivers: (1)18k Question{--}SQL pairs across 113 databases, 41{--}77{\%} larger than current English sets; (2)55{\%} queries in the Ultra band of our four-level difficulty taxonomy; (3)87.5{\%} inter-annotator agreement; (4){\ensuremath{\geq}}80{\%} labour and {\ensuremath{\geq}}98{\%} monetary savings versus earlier efforts.Baselines including GPT-4o, Llama3, RESDSQL, and MAC-SQL, achieve at most 56{\%} execution accuracy, indicating substantial room for improvement."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2025-high">
<titleInfo>
<title>High-Quality Complex Text-to-SQL Data Generation through Chain-of-Verification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yuchen</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuze</namePart>
<namePart type="family">Gao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bin</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenfeng</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shuo</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jian</namePart>
<namePart type="family">Su</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kentaro</namePart>
<namePart type="family">Inui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haofen</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Derek</namePart>
<namePart type="given">F</namePart>
<namePart type="family">Wong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pushpak</namePart>
<namePart type="family">Bhattacharyya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Biplab</namePart>
<namePart type="family">Banerjee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asif</namePart>
<namePart type="family">Ekbal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dhirendra</namePart>
<namePart type="given">Pratap</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>The Asian Federation of Natural Language Processing and The Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mumbai, India</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-303-6</identifier>
</relatedItem>
<abstract>Can today’s Text-to-SQL benchmarks still stretch modern LLMs? We argue no. Spider1.0 and BIRD, painstakingly hand-built, remain small, costly, and skewed toward middle complex SQL. Meanwhile, LLM-generated corpora are inexpensive but often superficial and fragile suffering from shallow nesting, semantic drift, template fatigue, and insufficient quality check.We address this gap with a Chain-of-Verifications framework that turns a handful of expert-labelled seeds into a large, reliably checked dataset at a fraction of the usual cost. The resulting corpus, AIGT2S, delivers: (1)18k Question–SQL pairs across 113 databases, 41–77% larger than current English sets; (2)55% queries in the Ultra band of our four-level difficulty taxonomy; (3)87.5% inter-annotator agreement; (4)\ensuremath\geq80% labour and \ensuremath\geq98% monetary savings versus earlier efforts.Baselines including GPT-4o, Llama3, RESDSQL, and MAC-SQL, achieve at most 56% execution accuracy, indicating substantial room for improvement.</abstract>
<identifier type="citekey">zhang-etal-2025-high</identifier>
<location>
<url>https://aclanthology.org/2025.findings-ijcnlp.143/</url>
</location>
<part>
<date>2025-12</date>
<extent unit="page">
<start>2368</start>
<end>2379</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T High-Quality Complex Text-to-SQL Data Generation through Chain-of-Verification
%A Zhang, Yuchen
%A Gao, Yuze
%A Chen, Bin
%A Li, Wenfeng
%A Sun, Shuo
%A Su, Jian
%Y Inui, Kentaro
%Y Sakti, Sakriani
%Y Wang, Haofen
%Y Wong, Derek F.
%Y Bhattacharyya, Pushpak
%Y Banerjee, Biplab
%Y Ekbal, Asif
%Y Chakraborty, Tanmoy
%Y Singh, Dhirendra Pratap
%S Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics
%D 2025
%8 December
%I The Asian Federation of Natural Language Processing and The Association for Computational Linguistics
%C Mumbai, India
%@ 979-8-89176-303-6
%F zhang-etal-2025-high
%X Can today’s Text-to-SQL benchmarks still stretch modern LLMs? We argue no. Spider1.0 and BIRD, painstakingly hand-built, remain small, costly, and skewed toward middle complex SQL. Meanwhile, LLM-generated corpora are inexpensive but often superficial and fragile suffering from shallow nesting, semantic drift, template fatigue, and insufficient quality check.We address this gap with a Chain-of-Verifications framework that turns a handful of expert-labelled seeds into a large, reliably checked dataset at a fraction of the usual cost. The resulting corpus, AIGT2S, delivers: (1)18k Question–SQL pairs across 113 databases, 41–77% larger than current English sets; (2)55% queries in the Ultra band of our four-level difficulty taxonomy; (3)87.5% inter-annotator agreement; (4)\ensuremath\geq80% labour and \ensuremath\geq98% monetary savings versus earlier efforts.Baselines including GPT-4o, Llama3, RESDSQL, and MAC-SQL, achieve at most 56% execution accuracy, indicating substantial room for improvement.
%U https://aclanthology.org/2025.findings-ijcnlp.143/
%P 2368-2379
Markdown (Informal)
[High-Quality Complex Text-to-SQL Data Generation through Chain-of-Verification](https://aclanthology.org/2025.findings-ijcnlp.143/) (Zhang et al., Findings 2025)
ACL
- Yuchen Zhang, Yuze Gao, Bin Chen, Wenfeng Li, Shuo Sun, and Jian Su. 2025. High-Quality Complex Text-to-SQL Data Generation through Chain-of-Verification. In Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics, pages 2368–2379, Mumbai, India. The Asian Federation of Natural Language Processing and The Association for Computational Linguistics.