Agentic Verification for Ambiguous Query Disambiguation

Youngwon Lee; Seung-Won Hwang; Ruofan Wu; Feng Yan; Danmei Xu; Moutasem Akkad; Zhewei Yao; Yuxiong He

Agentic Verification for Ambiguous Query Disambiguation

Youngwon Lee, Seung-won Hwang, Ruofan Wu, Feng Yan, Danmei Xu, Moutasem Akkad, Zhewei Yao, Yuxiong He

Correct Metadata for

Use this form to create a GitHub issue with structured data describing the correction. You will need a GitHub account. Once you create that issue, the correction will be reviewed by a staff member.

⚠️ Mobile Users: Submitting this form to create a new issue will only work with github.com, not the GitHub Mobile app.

Important: The Anthology treat PDFs as authoritative. Please use this form only to correct data that is out of line with the PDF. See our corrections guidelines if you need to change the PDF.

Title Adjust the title. Retain tags such as <fixed-case>.

Authors Adjust author names and order to match the PDF.

Abstract Correct abstract if needed. Retain XML formatting tags such as <tex-math>. You may use <b>...</b> for bold, <i>...</i> for italic, and <url>...</url> for URLs.

Verification against PDF Ensure that the new title/authors match the snapshot below. (If there is no snapshot or it is too small, consult the PDF.)

Authors concatenated from the text boxes above:

ALL author names match the snapshot above—including middle initials, hyphens, and accents.

Abstract

We study ambiguous-query disambiguation in retrieval-augmented generation (RAG). Prior Diversify-then-Verify (DtV) pipelines first generate interpretations and then retrieve evidence, often introducing ungrounded queries that cannot be answered from the corpus and requiring costly post-hoc pruning and verification. We propose VerDICT, a novel approach that unifies diversification with verification by integrating retriever relevance and generator answerability feedback early. This not only reduces cascading errors but also enables parallelism. On ASQA, VerDICT improves grounding-aware F1 by an average of 23% over the strongest baselines across multiple LLM backbones.

Anthology ID:: 2026.findings-acl.1932
Volume:: Findings of the Association for Computational Linguistics: ACL 2026
Month:: July
Year:: 2026
Address:: San Diego, California, United States
Editors:: Maria Liakata, Viviane P. Moreira, Jiajun Zhang, David Jurgens
Venue:: Findings
SIG:
Publisher:: Association for Computational Linguistics
Note:
Pages:: 38781–38796
Language:
URL:: https://aclanthology.org/2026.findings-acl.1932/
DOI:
Bibkey:
Cite (ACL):: Youngwon Lee, Seung-won Hwang, Ruofan Wu, Feng Yan, Danmei Xu, Moutasem Akkad, Zhewei Yao, and Yuxiong He. 2026. Agentic Verification for Ambiguous Query Disambiguation. In Findings of the Association for Computational Linguistics: ACL 2026, pages 38781–38796, San Diego, California, United States. Association for Computational Linguistics.
Cite (Informal):: Agentic Verification for Ambiguous Query Disambiguation (Lee et al., Findings 2026)
Copy Citation:
PDF:: https://aclanthology.org/2026.findings-acl.1932.pdf
Checklist:: 2026.findings-acl.1932.checklist.pdf

PDF Cite Search Checklist Fix data

Export citation

BibTeX
MODS XML
Endnote
Preformatted

@inproceedings{lee-etal-2026-agentic,
    title = "Agentic Verification for Ambiguous Query Disambiguation",
    author = "Lee, Youngwon  and
      Hwang, Seung-won  and
      Wu, Ruofan  and
      Yan, Feng  and
      Xu, Danmei  and
      Akkad, Moutasem  and
      Yao, Zhewei  and
      He, Yuxiong",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.findings-acl.1932/",
    pages = "38781--38796",
    ISBN = "979-8-89176-395-1",
    abstract = "We study ambiguous-query disambiguation in retrieval-augmented generation (RAG). Prior Diversify-then-Verify (DtV) pipelines first generate interpretations and then retrieve evidence, often introducing ungrounded queries that cannot be answered from the corpus and requiring costly post-hoc pruning and verification. We propose VerDICT, a novel approach that unifies diversification with verification by integrating retriever relevance and generator answerability feedback early. This not only reduces cascading errors but also enables parallelism. On ASQA, VerDICT improves grounding-aware F1 by an average of 23{\%} over the strongest baselines across multiple LLM backbones."
}

Download as File

<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lee-etal-2026-agentic">
    <titleInfo>
        <title>Agentic Verification for Ambiguous Query Disambiguation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Youngwon</namePart>
        <namePart type="family">Lee</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Seung-won</namePart>
        <namePart type="family">Hwang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ruofan</namePart>
        <namePart type="family">Wu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Feng</namePart>
        <namePart type="family">Yan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Danmei</namePart>
        <namePart type="family">Xu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Moutasem</namePart>
        <namePart type="family">Akkad</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Zhewei</namePart>
        <namePart type="family">Yao</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yuxiong</namePart>
        <namePart type="family">He</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>Findings of the Association for Computational Linguistics: ACL 2026</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">979-8-89176-395-1</identifier>
    </relatedItem>
    <abstract>We study ambiguous-query disambiguation in retrieval-augmented generation (RAG). Prior Diversify-then-Verify (DtV) pipelines first generate interpretations and then retrieve evidence, often introducing ungrounded queries that cannot be answered from the corpus and requiring costly post-hoc pruning and verification. We propose VerDICT, a novel approach that unifies diversification with verification by integrating retriever relevance and generator answerability feedback early. This not only reduces cascading errors but also enables parallelism. On ASQA, VerDICT improves grounding-aware F1 by an average of 23% over the strongest baselines across multiple LLM backbones.</abstract>
    <identifier type="citekey">lee-etal-2026-agentic</identifier>
    <location>
        <url>https://aclanthology.org/2026.findings-acl.1932/</url>
    </location>
    <part>
        <date>2026-07</date>
        <extent unit="page">
            <start>38781</start>
            <end>38796</end>
        </extent>
    </part>
</mods>
</modsCollection>

Download as File

%0 Conference Proceedings
%T Agentic Verification for Ambiguous Query Disambiguation
%A Lee, Youngwon
%A Hwang, Seung-won
%A Wu, Ruofan
%A Yan, Feng
%A Xu, Danmei
%A Akkad, Moutasem
%A Yao, Zhewei
%A He, Yuxiong
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Findings of the Association for Computational Linguistics: ACL 2026
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-395-1
%F lee-etal-2026-agentic
%X We study ambiguous-query disambiguation in retrieval-augmented generation (RAG). Prior Diversify-then-Verify (DtV) pipelines first generate interpretations and then retrieve evidence, often introducing ungrounded queries that cannot be answered from the corpus and requiring costly post-hoc pruning and verification. We propose VerDICT, a novel approach that unifies diversification with verification by integrating retriever relevance and generator answerability feedback early. This not only reduces cascading errors but also enables parallelism. On ASQA, VerDICT improves grounding-aware F1 by an average of 23% over the strongest baselines across multiple LLM backbones.
%U https://aclanthology.org/2026.findings-acl.1932/
%P 38781-38796

Download as File

Markdown (Informal)

[Agentic Verification for Ambiguous Query Disambiguation](https://aclanthology.org/2026.findings-acl.1932/) (Lee et al., Findings 2026)

Agentic Verification for Ambiguous Query Disambiguation (Lee et al., Findings 2026)

ACL

Youngwon Lee, Seung-won Hwang, Ruofan Wu, Feng Yan, Danmei Xu, Moutasem Akkad, Zhewei Yao, and Yuxiong He. 2026. Agentic Verification for Ambiguous Query Disambiguation. In Findings of the Association for Computational Linguistics: ACL 2026, pages 38781–38796, San Diego, California, United States. Association for Computational Linguistics.