@inproceedings{ji-etal-2026-text,
title = "Text-to-{SQL} Benchmarks Toward Enterprise Realities: Under Massive Scopes, Complex Schemas and Scattered Knowledge",
author = "Ji, Yuchen and
Yu, Chengxi and
Shi, Jie and
Zhou, Weixin and
Cao, Xi and
Liang, Jiaqing and
Chen, Hai and
Mao, Yu and
Yang, Deqing and
Xiao, Yanghua",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-emnlp.1971/",
doi = "10.18653/2026.findings-emnlp.1971",
pages = "42028--42060",
ISBN = "979-8-89176-462-0",
abstract = "Existing Text-to-SQL benchmarks remain idealized compared with enterprise scenarios, which require massive query scopes, complex schemas, and scattered external knowledge. We present BIRD-Ent and Spider-Ent, two enterprise-oriented benchmarks constructed via a refinement framework, together with Dual-Retrieval-Augmented-Generation (DRAG) Text-to-SQL, which formalizes table-schema and knowledge retrieval before SQL generation. The benchmarks feature over 4,000 columns per query and, for BIRD-Ent, documents totaling 1.5M tokens. Evaluation on state-of-the-art models shows sharp drops, with only 39.1{\%} EX on BIRD-Ent and 60.5{\%} EX on Spider-Ent. These results establish the Ent-series as a discriminative testbed for structurally robust and retrieval-aware Text-to-SQL."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ji-etal-2026-text">
<titleInfo>
<title>Text-to-SQL Benchmarks Toward Enterprise Realities: Under Massive Scopes, Complex Schemas and Scattered Knowledge</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yuchen</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chengxi</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jie</namePart>
<namePart type="family">Shi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Weixin</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xi</namePart>
<namePart type="family">Cao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiaqing</namePart>
<namePart type="family">Liang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hai</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yu</namePart>
<namePart type="family">Mao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Deqing</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yanghua</namePart>
<namePart type="family">Xiao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-462-0</identifier>
</relatedItem>
<abstract>Existing Text-to-SQL benchmarks remain idealized compared with enterprise scenarios, which require massive query scopes, complex schemas, and scattered external knowledge. We present BIRD-Ent and Spider-Ent, two enterprise-oriented benchmarks constructed via a refinement framework, together with Dual-Retrieval-Augmented-Generation (DRAG) Text-to-SQL, which formalizes table-schema and knowledge retrieval before SQL generation. The benchmarks feature over 4,000 columns per query and, for BIRD-Ent, documents totaling 1.5M tokens. Evaluation on state-of-the-art models shows sharp drops, with only 39.1% EX on BIRD-Ent and 60.5% EX on Spider-Ent. These results establish the Ent-series as a discriminative testbed for structurally robust and retrieval-aware Text-to-SQL.</abstract>
<identifier type="citekey">ji-etal-2026-text</identifier>
<identifier type="doi">10.18653/2026.findings-emnlp.1971</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.1971/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>42028</start>
<end>42060</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Text-to-SQL Benchmarks Toward Enterprise Realities: Under Massive Scopes, Complex Schemas and Scattered Knowledge
%A Ji, Yuchen
%A Yu, Chengxi
%A Shi, Jie
%A Zhou, Weixin
%A Cao, Xi
%A Liang, Jiaqing
%A Chen, Hai
%A Mao, Yu
%A Yang, Deqing
%A Xiao, Yanghua
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F ji-etal-2026-text
%X Existing Text-to-SQL benchmarks remain idealized compared with enterprise scenarios, which require massive query scopes, complex schemas, and scattered external knowledge. We present BIRD-Ent and Spider-Ent, two enterprise-oriented benchmarks constructed via a refinement framework, together with Dual-Retrieval-Augmented-Generation (DRAG) Text-to-SQL, which formalizes table-schema and knowledge retrieval before SQL generation. The benchmarks feature over 4,000 columns per query and, for BIRD-Ent, documents totaling 1.5M tokens. Evaluation on state-of-the-art models shows sharp drops, with only 39.1% EX on BIRD-Ent and 60.5% EX on Spider-Ent. These results establish the Ent-series as a discriminative testbed for structurally robust and retrieval-aware Text-to-SQL.
%R 10.18653/2026.findings-emnlp.1971
%U https://aclanthology.org/2026.findings-emnlp.1971/
%U https://doi.org/10.18653/2026.findings-emnlp.1971
%P 42028-42060
Markdown (Informal)
[Text-to-SQL Benchmarks Toward Enterprise Realities: Under Massive Scopes, Complex Schemas and Scattered Knowledge](https://aclanthology.org/2026.findings-emnlp.1971/) (Ji et al., Findings 2026)
ACL
- Yuchen Ji, Chengxi Yu, Jie Shi, Weixin Zhou, Xi Cao, Jiaqing Liang, Hai Chen, Yu Mao, Deqing Yang, and Yanghua Xiao. 2026. Text-to-SQL Benchmarks Toward Enterprise Realities: Under Massive Scopes, Complex Schemas and Scattered Knowledge. In Findings of the Association for Computational Linguistics: EMNLP 2026, pages 42028–42060, Budapest, Hungary. Association for Computational Linguistics.