GQC: LLM-Based Grouped QA Consolidation for Open-Domain Fact Verification at AVeriTeC

Dongzhuoran Zhou; Roxana Pop; Yuqicheng Zhu; Evgeny Kharlamov

doi:10.18653/v1/2025.fever-1.11

GQC: LLM-Based Grouped QA Consolidation for Open-Domain Fact Verification at AVeriTeC

Dongzhuoran Zhou, Roxana Pop, Yuqicheng Zhu, Evgeny Kharlamov

Correct Metadata for

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>.

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

Structured fact verification benchmarks like AVeriTeC decompose claims into QA pairs to support fine-grained reasoning. However, current systems generate QA pairs independently for each evidence sentence, leading to redundancy, drift, and noise. We introduce a modular LLM-based QA consolidation module that jointly filters, clusters, and rewrites QA pairs at the claim level. Experiments show that this method improves evidence quality and veracity prediction accuracy. Our analysis also highlights the impact of model scale and alignment on downstream performance.

Anthology ID:: 2025.fever-1.11
Volume:: Proceedings of the Eighth Fact Extraction and VERification Workshop (FEVER)
Month:: July
Year:: 2025
Address:: Vienna, Austria
Editors:: Mubashara Akhtar, Rami Aly, Christos Christodoulopoulos, Oana Cocarascu, Zhijiang Guo, Arpit Mittal, Michael Schlichtkrull, James Thorne, Andreas Vlachos
Venues:: FEVER | WS
SIG:
Publisher:: Association for Computational Linguistics
Note:
Pages:: 151–161
Language:
URL:: https://aclanthology.org/2025.fever-1.11/
DOI:: 10.18653/v1/2025.fever-1.11
Bibkey:
Cite (ACL):: Dongzhuoran Zhou, Roxana Pop, Yuqicheng Zhu, and Evgeny Kharlamov. 2025. GQC: LLM-Based Grouped QA Consolidation for Open-Domain Fact Verification at AVeriTeC. In Proceedings of the Eighth Fact Extraction and VERification Workshop (FEVER), pages 151–161, Vienna, Austria. Association for Computational Linguistics.
Cite (Informal):: GQC: LLM-Based Grouped QA Consolidation for Open-Domain Fact Verification at AVeriTeC (Zhou et al., FEVER 2025)
Copy Citation:
PDF:: https://aclanthology.org/2025.fever-1.11.pdf

PDF Cite Search Fix data

Export citation

BibTeX
MODS XML
Endnote
Preformatted

@inproceedings{zhou-etal-2025-gqc,
    title = "{GQC}: {LLM}-Based Grouped {QA} Consolidation for Open-Domain Fact Verification at {AV}eri{T}e{C}",
    author = "Zhou, Dongzhuoran  and
      Pop, Roxana  and
      Zhu, Yuqicheng  and
      Kharlamov, Evgeny",
    editor = "Akhtar, Mubashara  and
      Aly, Rami  and
      Christodoulopoulos, Christos  and
      Cocarascu, Oana  and
      Guo, Zhijiang  and
      Mittal, Arpit  and
      Schlichtkrull, Michael  and
      Thorne, James  and
      Vlachos, Andreas",
    booktitle = "Proceedings of the Eighth Fact Extraction and VERification Workshop (FEVER)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2025.fever-1.11/",
    doi = "10.18653/v1/2025.fever-1.11",
    pages = "151--161",
    ISBN = "978-1-959429-53-1",
    abstract = "Structured fact verification benchmarks like AVeriTeC decompose claims into QA pairs to support fine-grained reasoning. However, current systems generate QA pairs independently for each evidence sentence, leading to redundancy, drift, and noise. We introduce a modular LLM-based QA consolidation module that jointly filters, clusters, and rewrites QA pairs at the claim level. Experiments show that this method improves evidence quality and veracity prediction accuracy. Our analysis also highlights the impact of model scale and alignment on downstream performance."
}

Download as File

<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhou-etal-2025-gqc">
    <titleInfo>
        <title>GQC: LLM-Based Grouped QA Consolidation for Open-Domain Fact Verification at AVeriTeC</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Dongzhuoran</namePart>
        <namePart type="family">Zhou</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Roxana</namePart>
        <namePart type="family">Pop</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yuqicheng</namePart>
        <namePart type="family">Zhu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Evgeny</namePart>
        <namePart type="family">Kharlamov</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the Eighth Fact Extraction and VERification Workshop (FEVER)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Mubashara</namePart>
            <namePart type="family">Akhtar</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Rami</namePart>
            <namePart type="family">Aly</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Christos</namePart>
            <namePart type="family">Christodoulopoulos</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Oana</namePart>
            <namePart type="family">Cocarascu</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Zhijiang</namePart>
            <namePart type="family">Guo</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Arpit</namePart>
            <namePart type="family">Mittal</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Michael</namePart>
            <namePart type="family">Schlichtkrull</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">James</namePart>
            <namePart type="family">Thorne</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Andreas</namePart>
            <namePart type="family">Vlachos</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Vienna, Austria</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">978-1-959429-53-1</identifier>
    </relatedItem>
    <abstract>Structured fact verification benchmarks like AVeriTeC decompose claims into QA pairs to support fine-grained reasoning. However, current systems generate QA pairs independently for each evidence sentence, leading to redundancy, drift, and noise. We introduce a modular LLM-based QA consolidation module that jointly filters, clusters, and rewrites QA pairs at the claim level. Experiments show that this method improves evidence quality and veracity prediction accuracy. Our analysis also highlights the impact of model scale and alignment on downstream performance.</abstract>
    <identifier type="citekey">zhou-etal-2025-gqc</identifier>
    <identifier type="doi">10.18653/v1/2025.fever-1.11</identifier>
    <location>
        <url>https://aclanthology.org/2025.fever-1.11/</url>
    </location>
    <part>
        <date>2025-07</date>
        <extent unit="page">
            <start>151</start>
            <end>161</end>
        </extent>
    </part>
</mods>
</modsCollection>

Download as File

%0 Conference Proceedings
%T GQC: LLM-Based Grouped QA Consolidation for Open-Domain Fact Verification at AVeriTeC
%A Zhou, Dongzhuoran
%A Pop, Roxana
%A Zhu, Yuqicheng
%A Kharlamov, Evgeny
%Y Akhtar, Mubashara
%Y Aly, Rami
%Y Christodoulopoulos, Christos
%Y Cocarascu, Oana
%Y Guo, Zhijiang
%Y Mittal, Arpit
%Y Schlichtkrull, Michael
%Y Thorne, James
%Y Vlachos, Andreas
%S Proceedings of the Eighth Fact Extraction and VERification Workshop (FEVER)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 978-1-959429-53-1
%F zhou-etal-2025-gqc
%X Structured fact verification benchmarks like AVeriTeC decompose claims into QA pairs to support fine-grained reasoning. However, current systems generate QA pairs independently for each evidence sentence, leading to redundancy, drift, and noise. We introduce a modular LLM-based QA consolidation module that jointly filters, clusters, and rewrites QA pairs at the claim level. Experiments show that this method improves evidence quality and veracity prediction accuracy. Our analysis also highlights the impact of model scale and alignment on downstream performance.
%R 10.18653/v1/2025.fever-1.11
%U https://aclanthology.org/2025.fever-1.11/
%U https://doi.org/10.18653/v1/2025.fever-1.11
%P 151-161

Download as File

Markdown (Informal)

[GQC: LLM-Based Grouped QA Consolidation for Open-Domain Fact Verification at AVeriTeC](https://aclanthology.org/2025.fever-1.11/) (Zhou et al., FEVER 2025)

GQC: LLM-Based Grouped QA Consolidation for Open-Domain Fact Verification at AVeriTeC (Zhou et al., FEVER 2025)

ACL

Dongzhuoran Zhou, Roxana Pop, Yuqicheng Zhu, and Evgeny Kharlamov. 2025. GQC: LLM-Based Grouped QA Consolidation for Open-Domain Fact Verification at AVeriTeC. In Proceedings of the Eighth Fact Extraction and VERification Workshop (FEVER), pages 151–161, Vienna, Austria. Association for Computational Linguistics.