<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zheng-yang-2026-njustkmg">
    <titleInfo>
        <title>NJUSTKMG at SemEval 2026 Task 10 PsyCoMark—Subtask 2:Conspiracy Detection</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Yuhan</namePart>
        <namePart type="family">Zheng</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yang</namePart>
        <namePart type="family">Yang</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 describes our system designed forSemEval-2026 Task 10: PsyCoMark—Subtask2: Conspiracy Detection. We proposed a two-stage approach that leverages large-scale pre-trained models and a fine-tuned smaller modelto detect conspiracy theories in text. In thefirst stage, we utilize a large model to test allthe test samples and filter out those that areclearly unrelated to conspiracy theories. Forthe remaining samples, we apply a retrieval-enhanced custom prompt strategy combinedwith the Roberta-Large model in the secondstage. This allows us to fine-tune the modelwith weighted predictions based on relevantretrieved information, enhancing detection ac-curacy. Our system achieved first place onthe leaderboard, with an impressive F1 Scoreof 0.8874. We also present a brief analysisof the effectiveness of the methods used, in-cluding the advantages and limitations of largemodel-based filtering and retrieval-augmentedfine-tuning.</abstract>
    <identifier type="citekey">zheng-yang-2026-njustkmg</identifier>
    <location>
        <url>https://aclanthology.org/2026.semeval-1.128/</url>
    </location>
    <part>
        <date>2026-07</date>
        <extent unit="page">
            <start>932</start>
            <end>937</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T NJUSTKMG at SemEval 2026 Task 10 PsyCoMark—Subtask 2:Conspiracy Detection
%A Zheng, Yuhan
%A Yang, Yang
%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 zheng-yang-2026-njustkmg
%X This paper describes our system designed forSemEval-2026 Task 10: PsyCoMark—Subtask2: Conspiracy Detection. We proposed a two-stage approach that leverages large-scale pre-trained models and a fine-tuned smaller modelto detect conspiracy theories in text. In thefirst stage, we utilize a large model to test allthe test samples and filter out those that areclearly unrelated to conspiracy theories. Forthe remaining samples, we apply a retrieval-enhanced custom prompt strategy combinedwith the Roberta-Large model in the secondstage. This allows us to fine-tune the modelwith weighted predictions based on relevantretrieved information, enhancing detection ac-curacy. Our system achieved first place onthe leaderboard, with an impressive F1 Scoreof 0.8874. We also present a brief analysisof the effectiveness of the methods used, in-cluding the advantages and limitations of largemodel-based filtering and retrieval-augmentedfine-tuning.
%U https://aclanthology.org/2026.semeval-1.128/
%P 932-937

Markdown (Informal)

[NJUSTKMG at SemEval 2026 Task 10 PsyCoMark—Subtask 2:Conspiracy Detection](https://aclanthology.org/2026.semeval-1.128/) (Zheng & Yang, SemEval 2026)

• NJUSTKMG at SemEval 2026 Task 10 PsyCoMark—Subtask 2:Conspiracy Detection (Zheng & Yang, SemEval 2026)

ACL

• Yuhan Zheng and Yang Yang. 2026. NJUSTKMG at SemEval 2026 Task 10 PsyCoMark—Subtask 2:Conspiracy Detection. In Proceedings of the 20th International Workshop on Semantic Evaluation (2026), pages 932–937, San Diego, California, USA. Association for Computational Linguistics.