@inproceedings{xie-etal-2026-sde,
title = "{SDE}-{SQL}: Enhancing Text-to-{SQL} Generation in Large Language Models via Self-Driven Exploration with {SQL} Probes",
author = "Xie, Wenxuan and
Dai, Yaxun and
Jiang, Wenhao",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.acl-long.116/",
pages = "2507--2525",
ISBN = "979-8-89176-390-6",
abstract = "Recent advances in large language models (LLMs) have led to substantial progress on the Text-to-SQL task. However, existing approaches typically depend on static, pre-processed database information supplied at inference time, which restricts the model{'}s capacity to deeply comprehend the underlying database content. In the absence of dynamic interaction, LLMs are limited to fixed, human-curated context and lack the ability to autonomously query or explore the data. To overcome this limitation, we introduce $\textbf{SDE-SQL}$, a novel framework that empowers LLMs to perform $\textbf{Self-Driven Exploration}$ of databases during inference. This is achieved through the generation and execution of $\textbf{SQL probes}$, enabling the model to actively retrieve information and iteratively refine its understanding of the database. Unlike prior methods, $\textbf{SDE-SQL}$ operates in a $\textbf{zero-shot}$ setting, requiring no in-context demonstrations or question-SQL pairs. Evaluated on the BIRD benchmark with $Qwen2.5-72B-Instruct$, $\textbf{SDE-SQL}$ achieves an $\textbf{8.02}$ {\%} relative improvement in execution accuracy over the vanilla $Qwen2.5-72B-Instruct$ baseline, establishing a new state-of-the-art among open-source methods without supervised fine-tuning (SFT) or model ensembling. Furthermore, when combined with SFT, $\textbf{SDE-SQL}$ delivers an additional $\textbf{0.52}$ {\%} performance gain."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xie-etal-2026-sde">
<titleInfo>
<title>SDE-SQL: Enhancing Text-to-SQL Generation in Large Language Models via Self-Driven Exploration with SQL Probes</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wenxuan</namePart>
<namePart type="family">Xie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yaxun</namePart>
<namePart type="family">Dai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenhao</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Liakata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viviane</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Moreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Jurgens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-390-6</identifier>
</relatedItem>
<abstract>Recent advances in large language models (LLMs) have led to substantial progress on the Text-to-SQL task. However, existing approaches typically depend on static, pre-processed database information supplied at inference time, which restricts the model’s capacity to deeply comprehend the underlying database content. In the absence of dynamic interaction, LLMs are limited to fixed, human-curated context and lack the ability to autonomously query or explore the data. To overcome this limitation, we introduce SDE-SQL, a novel framework that empowers LLMs to perform Self-Driven Exploration of databases during inference. This is achieved through the generation and execution of SQL probes, enabling the model to actively retrieve information and iteratively refine its understanding of the database. Unlike prior methods, SDE-SQL operates in a zero-shot setting, requiring no in-context demonstrations or question-SQL pairs. Evaluated on the BIRD benchmark with Qwen2.5-72B-Instruct, SDE-SQL achieves an 8.02 % relative improvement in execution accuracy over the vanilla Qwen2.5-72B-Instruct baseline, establishing a new state-of-the-art among open-source methods without supervised fine-tuning (SFT) or model ensembling. Furthermore, when combined with SFT, SDE-SQL delivers an additional 0.52 % performance gain.</abstract>
<identifier type="citekey">xie-etal-2026-sde</identifier>
<location>
<url>https://aclanthology.org/2026.acl-long.116/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>2507</start>
<end>2525</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SDE-SQL: Enhancing Text-to-SQL Generation in Large Language Models via Self-Driven Exploration with SQL Probes
%A Xie, Wenxuan
%A Dai, Yaxun
%A Jiang, Wenhao
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-390-6
%F xie-etal-2026-sde
%X Recent advances in large language models (LLMs) have led to substantial progress on the Text-to-SQL task. However, existing approaches typically depend on static, pre-processed database information supplied at inference time, which restricts the model’s capacity to deeply comprehend the underlying database content. In the absence of dynamic interaction, LLMs are limited to fixed, human-curated context and lack the ability to autonomously query or explore the data. To overcome this limitation, we introduce SDE-SQL, a novel framework that empowers LLMs to perform Self-Driven Exploration of databases during inference. This is achieved through the generation and execution of SQL probes, enabling the model to actively retrieve information and iteratively refine its understanding of the database. Unlike prior methods, SDE-SQL operates in a zero-shot setting, requiring no in-context demonstrations or question-SQL pairs. Evaluated on the BIRD benchmark with Qwen2.5-72B-Instruct, SDE-SQL achieves an 8.02 % relative improvement in execution accuracy over the vanilla Qwen2.5-72B-Instruct baseline, establishing a new state-of-the-art among open-source methods without supervised fine-tuning (SFT) or model ensembling. Furthermore, when combined with SFT, SDE-SQL delivers an additional 0.52 % performance gain.
%U https://aclanthology.org/2026.acl-long.116/
%P 2507-2525
Markdown (Informal)
[SDE-SQL: Enhancing Text-to-SQL Generation in Large Language Models via Self-Driven Exploration with SQL Probes](https://aclanthology.org/2026.acl-long.116/) (Xie et al., ACL 2026)
ACL