@inproceedings{gan-etal-2026-text,
title = "Text-to-(Single-or-Multi)-{SQL}: Bridging Real-World Needs with Spider$\mathbb{S}$",
author = "Gan, Yujian and
Ouyang, Xuan and
Lin, Yuxi and
Zhang, Zhilin and
Xie, Jinxia and
Routsis, Vassilis",
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.467/",
pages = "9792--9821",
ISBN = "979-8-89176-462-0",
abstract = "Text-to-SQL systems allow users to interact with databases using natural language, but most assume that each question must be answered by a single SQL query. In practical settings, some information needs are more reliably satisfied by generating multiple simpler SQL queries, which is not supported by existing benchmark or evaluation protocols. To address this gap, we introduce Spider$\mathbb{S}$, which, to the best of our knowledge, is the first benchmark for the Text-to-(Multi)-SQL task, supporting both single- and multi-query solutions within a unified evaluation framework. To enable this setting, we propose a flexible evaluation protocol that accepts any prediction covering the required information, regardless of query number or structure. Under our evaluation protocol, we evaluate several large language models on Spider$\mathbb{S}$ and find that allowing multi-query outputs improves execution accuracy. However, current models demonstrate fragility: even a minor prompt change from generating one SQL to generating one or more SQL can significantly degrade performance. To improve robustness, we introduce a lightweight router that decides whether to generate a single or multiple SQL for a given question, leading to substantial performance gains."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gan-etal-2026-text">
<titleInfo>
<title>Text-to-(Single-or-Multi)-SQL: Bridging Real-World Needs with Spider\mathbbS</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yujian</namePart>
<namePart type="family">Gan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuan</namePart>
<namePart type="family">Ouyang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuxi</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhilin</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jinxia</namePart>
<namePart type="family">Xie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vassilis</namePart>
<namePart type="family">Routsis</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>Text-to-SQL systems allow users to interact with databases using natural language, but most assume that each question must be answered by a single SQL query. In practical settings, some information needs are more reliably satisfied by generating multiple simpler SQL queries, which is not supported by existing benchmark or evaluation protocols. To address this gap, we introduce Spider\mathbbS, which, to the best of our knowledge, is the first benchmark for the Text-to-(Multi)-SQL task, supporting both single- and multi-query solutions within a unified evaluation framework. To enable this setting, we propose a flexible evaluation protocol that accepts any prediction covering the required information, regardless of query number or structure. Under our evaluation protocol, we evaluate several large language models on Spider\mathbbS and find that allowing multi-query outputs improves execution accuracy. However, current models demonstrate fragility: even a minor prompt change from generating one SQL to generating one or more SQL can significantly degrade performance. To improve robustness, we introduce a lightweight router that decides whether to generate a single or multiple SQL for a given question, leading to substantial performance gains.</abstract>
<identifier type="citekey">gan-etal-2026-text</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.467/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>9792</start>
<end>9821</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Text-to-(Single-or-Multi)-SQL: Bridging Real-World Needs with Spider\mathbbS
%A Gan, Yujian
%A Ouyang, Xuan
%A Lin, Yuxi
%A Zhang, Zhilin
%A Xie, Jinxia
%A Routsis, Vassilis
%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 gan-etal-2026-text
%X Text-to-SQL systems allow users to interact with databases using natural language, but most assume that each question must be answered by a single SQL query. In practical settings, some information needs are more reliably satisfied by generating multiple simpler SQL queries, which is not supported by existing benchmark or evaluation protocols. To address this gap, we introduce Spider\mathbbS, which, to the best of our knowledge, is the first benchmark for the Text-to-(Multi)-SQL task, supporting both single- and multi-query solutions within a unified evaluation framework. To enable this setting, we propose a flexible evaluation protocol that accepts any prediction covering the required information, regardless of query number or structure. Under our evaluation protocol, we evaluate several large language models on Spider\mathbbS and find that allowing multi-query outputs improves execution accuracy. However, current models demonstrate fragility: even a minor prompt change from generating one SQL to generating one or more SQL can significantly degrade performance. To improve robustness, we introduce a lightweight router that decides whether to generate a single or multiple SQL for a given question, leading to substantial performance gains.
%U https://aclanthology.org/2026.findings-emnlp.467/
%P 9792-9821
Markdown (Informal)
[Text-to-(Single-or-Multi)-SQL: Bridging Real-World Needs with Spiderđť•Š](https://aclanthology.org/2026.findings-emnlp.467/) (Gan et al., Findings 2026)
ACL