<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhu-2026-jia">
    <titleInfo>
        <title>JIA at SemEval-2026 Task 10: A Dual-Track System with BERT-based Encoders and LLMs for Conspiracy Analysis</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Jiayue</namePart>
        <namePart type="family">Zhu</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>This paper presents a dual-track system for conspiracy theory detection and psycholinguistic marker extraction. We evaluate multiple architectures, including DistilBERT, BERT-Base, DeBERTa-V3, RoBERTa, and instruction-tuned Qwen2.5 models. Qwen2.5-14B (full-shot) achieves the best performance with a Weighted F1-score of 0.80 in the detection task. Marker extraction remains challenging: while the fine-tuned LLM performs best on “Actors,” its limited generalization in categories such as “Evidence” and “Effect” highlights persistent semantic ambiguity.</abstract>
    <identifier type="citekey">zhu-2026-jia</identifier>
    <location>
        <url>https://aclanthology.org/2026.semeval-1.174/</url>
    </location>
    <part>
        <date>2026-07</date>
        <extent unit="page">
            <start>1332</start>
            <end>1339</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T JIA at SemEval-2026 Task 10: A Dual-Track System with BERT-based Encoders and LLMs for Conspiracy Analysis
%A Zhu, Jiayue
%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 zhu-2026-jia
%X This paper presents a dual-track system for conspiracy theory detection and psycholinguistic marker extraction. We evaluate multiple architectures, including DistilBERT, BERT-Base, DeBERTa-V3, RoBERTa, and instruction-tuned Qwen2.5 models. Qwen2.5-14B (full-shot) achieves the best performance with a Weighted F1-score of 0.80 in the detection task. Marker extraction remains challenging: while the fine-tuned LLM performs best on “Actors,” its limited generalization in categories such as “Evidence” and “Effect” highlights persistent semantic ambiguity.
%U https://aclanthology.org/2026.semeval-1.174/
%P 1332-1339

Markdown (Informal)

[JIA at SemEval-2026 Task 10: A Dual-Track System with BERT-based Encoders and LLMs for Conspiracy Analysis](https://aclanthology.org/2026.semeval-1.174/) (Zhu, SemEval 2026)

• JIA at SemEval-2026 Task 10: A Dual-Track System with BERT-based Encoders and LLMs for Conspiracy Analysis (Zhu, SemEval 2026)

ACL

• Jiayue Zhu. 2026. JIA at SemEval-2026 Task 10: A Dual-Track System with BERT-based Encoders and LLMs for Conspiracy Analysis. In Proceedings of the 20th International Workshop on Semantic Evaluation (2026), pages 1332–1339, San Diego, California, USA. Association for Computational Linguistics.