<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yin-etal-2026-probing">
    <titleInfo>
        <title>Probing Ambiguity: Adversarial Intent Resolution for Robust Text-to-SQL</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Youbing</namePart>
        <namePart type="family">Yin</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Xujun</namePart>
        <namePart type="family">Peng</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Muhammad</namePart>
        <namePart type="given">Sharif</namePart>
        <namePart type="family">Uddin</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Erin</namePart>
        <namePart type="family">Babinsky</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Daben</namePart>
        <namePart type="family">Liu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Anoop</namePart>
        <namePart type="family">Kumar</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>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing</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">979-8-89176-459-0</identifier>
    </relatedItem>
    <abstract>Text-to-SQL systems typically assume a one-to-one mapping between natural-language queries and correct SQL translations. In practice, however, many queries are inherently ambiguous, admitting multiple valid interpretations that yield distinct outputs. We introduce Adversarial Intent Resolution (AIR), a multi-agent framework that actively probes and resolves such ambiguity without any task-specific training. AIR first constructs competing interpretations, verifies through SQL execution that they produce genuinely different results, and generates targeted clarification questions grounded in the observed data differences. Evaluating on leading benchmarks for ambiguous questions, AIR demonstrates strong performance, efficiency, and robust cross-benchmark transferability. On the AMBROSIA benchmark under schema-only context—a realistic production setting where exposing the full database is infeasible—AIR outperforms IntentRL, the state-of-the-art reinforcement learning model, across all metrics (e.g., F1 0.679 vs. 0.618). Crucially, AIR exhibits only \sim7% performance degradation without the full database, compared to \sim20% for IntentRL. On the AmbiQT benchmark, where ambiguity arises from schema design rather than linguistic structure, AIR achieves higher F1 under both context settings without any benchmark-specific adaptation.</abstract>
    <identifier type="citekey">yin-etal-2026-probing</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-main.2446/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>55493</start>
            <end>55504</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Probing Ambiguity: Adversarial Intent Resolution for Robust Text-to-SQL
%A Yin, Youbing
%A Peng, Xujun
%A Uddin, Muhammad Sharif
%A Babinsky, Erin
%A Liu, Daben
%A Kumar, Anoop
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F yin-etal-2026-probing
%X Text-to-SQL systems typically assume a one-to-one mapping between natural-language queries and correct SQL translations. In practice, however, many queries are inherently ambiguous, admitting multiple valid interpretations that yield distinct outputs. We introduce Adversarial Intent Resolution (AIR), a multi-agent framework that actively probes and resolves such ambiguity without any task-specific training. AIR first constructs competing interpretations, verifies through SQL execution that they produce genuinely different results, and generates targeted clarification questions grounded in the observed data differences. Evaluating on leading benchmarks for ambiguous questions, AIR demonstrates strong performance, efficiency, and robust cross-benchmark transferability. On the AMBROSIA benchmark under schema-only context—a realistic production setting where exposing the full database is infeasible—AIR outperforms IntentRL, the state-of-the-art reinforcement learning model, across all metrics (e.g., F1 0.679 vs. 0.618). Crucially, AIR exhibits only \sim7% performance degradation without the full database, compared to \sim20% for IntentRL. On the AmbiQT benchmark, where ambiguity arises from schema design rather than linguistic structure, AIR achieves higher F1 under both context settings without any benchmark-specific adaptation.
%U https://aclanthology.org/2026.emnlp-main.2446/
%P 55493-55504

Markdown (Informal)

[Probing Ambiguity: Adversarial Intent Resolution for Robust Text-to-SQL](https://aclanthology.org/2026.emnlp-main.2446/) (Yin et al., EMNLP 2026)

• Probing Ambiguity: Adversarial Intent Resolution for Robust Text-to-SQL (Yin et al., EMNLP 2026)

ACL

• Youbing Yin, Xujun Peng, Muhammad Sharif Uddin, Erin Babinsky, Daben Liu, and Anoop Kumar. 2026. Probing Ambiguity: Adversarial Intent Resolution for Robust Text-to-SQL. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 55493–55504, Budapest, Hungary. Association for Computational Linguistics.