@inproceedings{xue-etal-2026-duales,
title = "{D}ual{ES}: Internalizing Query-Text Duality for Text-to-{ES} via Bidirectional Reasoning-Enhanced Supervision",
author = "Xue, Dongge and
Wang, Yuxiang and
Ruan, Tong",
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.1777/",
pages = "38006--38024",
ISBN = "979-8-89176-462-0",
abstract = "Text-to-ES aims to translate natural language into executable Elasticsearch(ES) queries. Unlike more open-ended reasoning tasks, such as mathematical reasoning, this problem is defined over a constrained domain-specific language, where the synergy between forward reasoning and backward reasoning can be more explicitly realized under strict structural constraints. While recent work has explored reasoning-oriented training and prompting in text-to-SQL, forward and backward reasoning have not been systematically studied in text-to-ES. In this paper, we systematically study the bidirectional duality of the text-to-ES task by establishing a bidirectional reasoning perspective across both training and prompting stages. We introduce two large-scale datasets, TERD and ETRD, for forward and backward reasoning, respectively, and propose DualES, a unified framework that combines the two. Experimental results show that our DualES-CoRE strategy sets a new State-of-the-Art(SOTA), achieving 69.23{\%} on LED and 50.14{\%} on BirdES. This corresponds to absolute execution accuracy gains of 6.92{\%} and 7.34{\%} over previous benchmarks, outperforming both open-source and closed-source baselines. We will release the datasets in the future."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xue-etal-2026-duales">
<titleInfo>
<title>DualES: Internalizing Query-Text Duality for Text-to-ES via Bidirectional Reasoning-Enhanced Supervision</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dongge</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuxiang</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tong</namePart>
<namePart type="family">Ruan</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-ES aims to translate natural language into executable Elasticsearch(ES) queries. Unlike more open-ended reasoning tasks, such as mathematical reasoning, this problem is defined over a constrained domain-specific language, where the synergy between forward reasoning and backward reasoning can be more explicitly realized under strict structural constraints. While recent work has explored reasoning-oriented training and prompting in text-to-SQL, forward and backward reasoning have not been systematically studied in text-to-ES. In this paper, we systematically study the bidirectional duality of the text-to-ES task by establishing a bidirectional reasoning perspective across both training and prompting stages. We introduce two large-scale datasets, TERD and ETRD, for forward and backward reasoning, respectively, and propose DualES, a unified framework that combines the two. Experimental results show that our DualES-CoRE strategy sets a new State-of-the-Art(SOTA), achieving 69.23% on LED and 50.14% on BirdES. This corresponds to absolute execution accuracy gains of 6.92% and 7.34% over previous benchmarks, outperforming both open-source and closed-source baselines. We will release the datasets in the future.</abstract>
<identifier type="citekey">xue-etal-2026-duales</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.1777/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>38006</start>
<end>38024</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DualES: Internalizing Query-Text Duality for Text-to-ES via Bidirectional Reasoning-Enhanced Supervision
%A Xue, Dongge
%A Wang, Yuxiang
%A Ruan, Tong
%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 xue-etal-2026-duales
%X Text-to-ES aims to translate natural language into executable Elasticsearch(ES) queries. Unlike more open-ended reasoning tasks, such as mathematical reasoning, this problem is defined over a constrained domain-specific language, where the synergy between forward reasoning and backward reasoning can be more explicitly realized under strict structural constraints. While recent work has explored reasoning-oriented training and prompting in text-to-SQL, forward and backward reasoning have not been systematically studied in text-to-ES. In this paper, we systematically study the bidirectional duality of the text-to-ES task by establishing a bidirectional reasoning perspective across both training and prompting stages. We introduce two large-scale datasets, TERD and ETRD, for forward and backward reasoning, respectively, and propose DualES, a unified framework that combines the two. Experimental results show that our DualES-CoRE strategy sets a new State-of-the-Art(SOTA), achieving 69.23% on LED and 50.14% on BirdES. This corresponds to absolute execution accuracy gains of 6.92% and 7.34% over previous benchmarks, outperforming both open-source and closed-source baselines. We will release the datasets in the future.
%U https://aclanthology.org/2026.findings-emnlp.1777/
%P 38006-38024
Markdown (Informal)
[DualES: Internalizing Query-Text Duality for Text-to-ES via Bidirectional Reasoning-Enhanced Supervision](https://aclanthology.org/2026.findings-emnlp.1777/) (Xue et al., Findings 2026)
ACL