<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shu-etal-2026-comhis">
    <titleInfo>
        <title>Comhis at SemEval-2026 Task 4: Embedding-Space Adaptation and LLM-Assisted Inference for Narrative Similarity</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Ke</namePart>
        <namePart type="family">Shu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Eetu</namePart>
        <namePart type="family">Mäkelä</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Mikko</namePart>
        <namePart type="family">Tolonen</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 present a two-stage system for the SemEval Narrative Similarity task that separates representation learning from comparative decision making. In Track B, we adapt a frozen large-scale embedding model using a lightweight projection layer trained with a triplet objective and hard example mining, producing a task-specific similarity space. In Track A, similarity scores derived from the adapted embedding space are incorporated into a large language model, which performs the final binary decision. On the official test set, our system achieves 0.68 accuracy on Track A and 0.66 on Track B, clearly outperforming the provided baselines and ranking 20th out of 44 teams on Track A and 10th out of 27 teams on Track B. These results demonstrate that efficient embedding adaptation combined with embedding-informed LLM reasoning is effective for modeling high-level narrative similarity.</abstract>
    <identifier type="citekey">shu-etal-2026-comhis</identifier>
    <location>
        <url>https://aclanthology.org/2026.semeval-1.118/</url>
    </location>
    <part>
        <date>2026-07</date>
        <extent unit="page">
            <start>862</start>
            <end>868</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Comhis at SemEval-2026 Task 4: Embedding-Space Adaptation and LLM-Assisted Inference for Narrative Similarity
%A Shu, Ke
%A Mäkelä, Eetu
%A Tolonen, Mikko
%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 shu-etal-2026-comhis
%X We present a two-stage system for the SemEval Narrative Similarity task that separates representation learning from comparative decision making. In Track B, we adapt a frozen large-scale embedding model using a lightweight projection layer trained with a triplet objective and hard example mining, producing a task-specific similarity space. In Track A, similarity scores derived from the adapted embedding space are incorporated into a large language model, which performs the final binary decision. On the official test set, our system achieves 0.68 accuracy on Track A and 0.66 on Track B, clearly outperforming the provided baselines and ranking 20th out of 44 teams on Track A and 10th out of 27 teams on Track B. These results demonstrate that efficient embedding adaptation combined with embedding-informed LLM reasoning is effective for modeling high-level narrative similarity.
%U https://aclanthology.org/2026.semeval-1.118/
%P 862-868

Markdown (Informal)

[Comhis at SemEval-2026 Task 4: Embedding-Space Adaptation and LLM-Assisted Inference for Narrative Similarity](https://aclanthology.org/2026.semeval-1.118/) (Shu et al., SemEval 2026)

• Comhis at SemEval-2026 Task 4: Embedding-Space Adaptation and LLM-Assisted Inference for Narrative Similarity (Shu et al., SemEval 2026)

ACL

• Ke Shu, Eetu Mäkelä, and Mikko Tolonen. 2026. Comhis at SemEval-2026 Task 4: Embedding-Space Adaptation and LLM-Assisted Inference for Narrative Similarity. In Proceedings of the 20th International Workshop on Semantic Evaluation (2026), pages 862–868, San Diego, California, USA. Association for Computational Linguistics.