Team HITS at SemEval-2026 Task 4:Enhancing narrative text embedding model training with hard negatives generation and self-distillation

Qian Zhou; Yi Fan; Wei Liu; Michael Strube

Team HITS at SemEval-2026 Task 4:Enhancing narrative text embedding model training with hard negatives generation and self-distillation

Qian Zhou, Yi Fan, Wei Liu, Michael Strube

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 first use Qwen2.5-32B-Instruct model to generate hard negatives from threenarrative dimensions. We then train a Qwen3-Embedding-8B model with a multi-negativecontrastive objective and use self-distllation.

Anthology ID:: 2026.semeval-1.338
Volume:: Proceedings of the 20th International Workshop on Semantic Evaluation (2026)
Month:: July
Year:: 2026
Address:: San Diego, California, USA
Editors:: Ekaterina Kochmar, Debanjan Ghosh, Kai North, Mamoru Komachi
Venues:: SemEval | WS
SIG:
Publisher:: Association for Computational Linguistics
Note:
Pages:: 2679–2688
Language:
URL:: https://aclanthology.org/2026.semeval-1.338/
DOI:
Bibkey:
Cite (ACL):: Qian Zhou, Yi Fan, Wei Liu, and Michael Strube. 2026. Team HITS at SemEval-2026 Task 4:Enhancing narrative text embedding model training with hard negatives generation and self-distillation. In Proceedings of the 20th International Workshop on Semantic Evaluation (2026), pages 2679–2688, San Diego, California, USA. Association for Computational Linguistics.
Cite (Informal):: Team HITS at SemEval-2026 Task 4:Enhancing narrative text embedding model training with hard negatives generation and self-distillation (Zhou et al., SemEval 2026)
Copy Citation:
PDF:: https://aclanthology.org/2026.semeval-1.338.pdf

PDF Cite Search Fix data

Export citation

BibTeX
MODS XML
Endnote
Preformatted

@inproceedings{zhou-etal-2026-team,
    title = "Team {HITS} at {S}em{E}val-2026 Task 4:Enhancing narrative text embedding model training with hard negatives generation and self-distillation",
    author = "Zhou, Qian  and
      Fan, Yi  and
      Liu, Wei  and
      Strube, Michael",
    editor = "Kochmar, Ekaterina  and
      Ghosh, Debanjan  and
      North, Kai  and
      Komachi, Mamoru",
    booktitle = "Proceedings of the 20th {I}nternational {W}orkshop on {S}emantic {E}valuation (2026)",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.semeval-1.338/",
    pages = "2679--2688",
    ISBN = "979-8-89176-414-9",
    abstract = "We first use Qwen2.5-32B-Instruct model to generate hard negatives from threenarrative dimensions. We then train a Qwen3-Embedding-8B model with a multi-negativecontrastive objective and use self-distllation."
}

Download as File

<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhou-etal-2026-team">
    <titleInfo>
        <title>Team HITS at SemEval-2026 Task 4:Enhancing narrative text embedding model training with hard negatives generation and self-distillation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Qian</namePart>
        <namePart type="family">Zhou</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yi</namePart>
        <namePart type="family">Fan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Wei</namePart>
        <namePart type="family">Liu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Michael</namePart>
        <namePart type="family">Strube</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>Proceedings of the 20th International Workshop on Semantic Evaluation (2026)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Ekaterina</namePart>
            <namePart type="family">Kochmar</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Debanjan</namePart>
            <namePart type="family">Ghosh</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Kai</namePart>
            <namePart type="family">North</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Mamoru</namePart>
            <namePart type="family">Komachi</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, USA</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-414-9</identifier>
    </relatedItem>
    <abstract>We first use Qwen2.5-32B-Instruct model to generate hard negatives from threenarrative dimensions. We then train a Qwen3-Embedding-8B model with a multi-negativecontrastive objective and use self-distllation.</abstract>
    <identifier type="citekey">zhou-etal-2026-team</identifier>
    <location>
        <url>https://aclanthology.org/2026.semeval-1.338/</url>
    </location>
    <part>
        <date>2026-07</date>
        <extent unit="page">
            <start>2679</start>
            <end>2688</end>
        </extent>
    </part>
</mods>
</modsCollection>

Download as File

%0 Conference Proceedings
%T Team HITS at SemEval-2026 Task 4:Enhancing narrative text embedding model training with hard negatives generation and self-distillation
%A Zhou, Qian
%A Fan, Yi
%A Liu, Wei
%A Strube, Michael
%Y Kochmar, Ekaterina
%Y Ghosh, Debanjan
%Y North, Kai
%Y Komachi, Mamoru
%S Proceedings of the 20th International Workshop on Semantic Evaluation (2026)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, USA
%@ 979-8-89176-414-9
%F zhou-etal-2026-team
%X We first use Qwen2.5-32B-Instruct model to generate hard negatives from threenarrative dimensions. We then train a Qwen3-Embedding-8B model with a multi-negativecontrastive objective and use self-distllation.
%U https://aclanthology.org/2026.semeval-1.338/
%P 2679-2688

Download as File

Markdown (Informal)

[Team HITS at SemEval-2026 Task 4:Enhancing narrative text embedding model training with hard negatives generation and self-distillation](https://aclanthology.org/2026.semeval-1.338/) (Zhou et al., SemEval 2026)

Team HITS at SemEval-2026 Task 4:Enhancing narrative text embedding model training with hard negatives generation and self-distillation (Zhou et al., SemEval 2026)

ACL

Qian Zhou, Yi Fan, Wei Liu, and Michael Strube. 2026. Team HITS at SemEval-2026 Task 4:Enhancing narrative text embedding model training with hard negatives generation and self-distillation. In Proceedings of the 20th International Workshop on Semantic Evaluation (2026), pages 2679–2688, San Diego, California, USA. Association for Computational Linguistics.