Team HUMANE at AVeriTeC 2025: HerO 2 for Efficient Fact Verification

Yejun Yoon; Jaeyoon Jung; Seunghyun Yoon; Kunwoo Park

doi:10.18653/v1/2025.fever-1.16

Team HUMANE at AVeriTeC 2025: HerO 2 for Efficient Fact Verification

Yejun Yoon, Jaeyoon Jung, Seunghyun Yoon, Kunwoo Park

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

This paper presents HerO 2, Team HUMANE’s system for the AVeriTeC shared task at the FEVER-25 workshop. HerO 2 is an enhanced version of HerO, the best-performing open-source model from the previous year’s challenge. It improves evidence quality through document summarization and answer reformulation, optimizes veracity prediction via post-training quantization under computational constraints, and enhances overall system performance by integrating updated language model (LM) backbones. HerO 2 ranked second on the leaderboard while achieving the shortest runtime among the top three systems, demonstrating both high efficiency and strong potential for real-world fact verification. The code is available at https://github.com/ssu-humane/HerO2.

Anthology ID:: 2025.fever-1.16
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:: 224–228
Language:
URL:: https://aclanthology.org/2025.fever-1.16/
DOI:: 10.18653/v1/2025.fever-1.16
Bibkey:
Cite (ACL):: Yejun Yoon, Jaeyoon Jung, Seunghyun Yoon, and Kunwoo Park. 2025. Team HUMANE at AVeriTeC 2025: HerO 2 for Efficient Fact Verification. In Proceedings of the Eighth Fact Extraction and VERification Workshop (FEVER), pages 224–228, Vienna, Austria. Association for Computational Linguistics.
Cite (Informal):: Team HUMANE at AVeriTeC 2025: HerO 2 for Efficient Fact Verification (Yoon et al., FEVER 2025)
Copy Citation:
PDF:: https://aclanthology.org/2025.fever-1.16.pdf

PDF Cite Search Fix data

Export citation

BibTeX
MODS XML
Endnote
Preformatted

@inproceedings{yoon-etal-2025-team,
    title = "Team {HUMANE} at {AV}eri{T}e{C} 2025: {H}er{O} 2 for Efficient Fact Verification",
    author = "Yoon, Yejun  and
      Jung, Jaeyoon  and
      Yoon, Seunghyun  and
      Park, Kunwoo",
    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-1.16/",
    doi = "10.18653/v1/2025.fever-1.16",
    pages = "224--228",
    ISBN = "978-1-959429-53-1",
    abstract = "This paper presents HerO 2, Team HUMANE{'}s system for the AVeriTeC shared task at the FEVER-25 workshop. HerO 2 is an enhanced version of HerO, the best-performing open-source model from the previous year{'}s challenge. It improves evidence quality through document summarization and answer reformulation, optimizes veracity prediction via post-training quantization under computational constraints, and enhances overall system performance by integrating updated language model (LM) backbones. HerO 2 ranked second on the leaderboard while achieving the shortest runtime among the top three systems, demonstrating both high efficiency and strong potential for real-world fact verification. The code is available at \url{https://github.com/ssu-humane/HerO2}."
}

Download as File

<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yoon-etal-2025-team">
    <titleInfo>
        <title>Team HUMANE at AVeriTeC 2025: HerO 2 for Efficient Fact Verification</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Yejun</namePart>
        <namePart type="family">Yoon</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jaeyoon</namePart>
        <namePart type="family">Jung</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Seunghyun</namePart>
        <namePart type="family">Yoon</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Kunwoo</namePart>
        <namePart type="family">Park</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>This paper presents HerO 2, Team HUMANE’s system for the AVeriTeC shared task at the FEVER-25 workshop. HerO 2 is an enhanced version of HerO, the best-performing open-source model from the previous year’s challenge. It improves evidence quality through document summarization and answer reformulation, optimizes veracity prediction via post-training quantization under computational constraints, and enhances overall system performance by integrating updated language model (LM) backbones. HerO 2 ranked second on the leaderboard while achieving the shortest runtime among the top three systems, demonstrating both high efficiency and strong potential for real-world fact verification. The code is available at https://github.com/ssu-humane/HerO2.</abstract>
    <identifier type="citekey">yoon-etal-2025-team</identifier>
    <identifier type="doi">10.18653/v1/2025.fever-1.16</identifier>
    <location>
        <url>https://aclanthology.org/2025.fever-1.16/</url>
    </location>
    <part>
        <date>2025-07</date>
        <extent unit="page">
            <start>224</start>
            <end>228</end>
        </extent>
    </part>
</mods>
</modsCollection>

Download as File

%0 Conference Proceedings
%T Team HUMANE at AVeriTeC 2025: HerO 2 for Efficient Fact Verification
%A Yoon, Yejun
%A Jung, Jaeyoon
%A Yoon, Seunghyun
%A Park, Kunwoo
%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 yoon-etal-2025-team
%X This paper presents HerO 2, Team HUMANE’s system for the AVeriTeC shared task at the FEVER-25 workshop. HerO 2 is an enhanced version of HerO, the best-performing open-source model from the previous year’s challenge. It improves evidence quality through document summarization and answer reformulation, optimizes veracity prediction via post-training quantization under computational constraints, and enhances overall system performance by integrating updated language model (LM) backbones. HerO 2 ranked second on the leaderboard while achieving the shortest runtime among the top three systems, demonstrating both high efficiency and strong potential for real-world fact verification. The code is available at https://github.com/ssu-humane/HerO2.
%R 10.18653/v1/2025.fever-1.16
%U https://aclanthology.org/2025.fever-1.16/
%U https://doi.org/10.18653/v1/2025.fever-1.16
%P 224-228

Download as File

Markdown (Informal)

[Team HUMANE at AVeriTeC 2025: HerO 2 for Efficient Fact Verification](https://aclanthology.org/2025.fever-1.16/) (Yoon et al., FEVER 2025)

Team HUMANE at AVeriTeC 2025: HerO 2 for Efficient Fact Verification (Yoon et al., FEVER 2025)

ACL

Yejun Yoon, Jaeyoon Jung, Seunghyun Yoon, and Kunwoo Park. 2025. Team HUMANE at AVeriTeC 2025: HerO 2 for Efficient Fact Verification. In Proceedings of the Eighth Fact Extraction and VERification Workshop (FEVER), pages 224–228, Vienna, Austria. Association for Computational Linguistics.