<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bazdyrev-etal-2025-transforming">
    <titleInfo>
        <title>Transforming Causal LLM into MLM Encoder for Detecting Social Media Manipulation in Telegram</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Anton</namePart>
        <namePart type="family">Bazdyrev</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ivan</namePart>
        <namePart type="family">Bashtovyi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ivan</namePart>
        <namePart type="family">Havlytskyi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Oleksandr</namePart>
        <namePart type="family">Kharytonov</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Artur</namePart>
        <namePart type="family">Khodakovskyi</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 Fourth Ukrainian Natural Language Processing Workshop (UNLP 2025)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Mariana</namePart>
            <namePart type="family">Romanyshyn</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Vienna, Austria (online)</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-269-5</identifier>
    </relatedItem>
    <abstract>We participated in the Fourth UNLP shared task on detecting social media manipulation in Ukrainian Telegram posts, addressing both multilabel technique classification and token-level span identification. We propose two complementary solutions: for classification, we fine-tune the decoder-only model with class-balanced grid-search thresholding and ensembling. For span detection, we convert causal LLM into a bidirectional encoder via masked language modeling pretraining on large Ukrainian and Russian news corpora before fine-tuning. Our solutions achieve SOTA metric results on both shared task track. Our work demonstrates the efficacy of bidirectional pretraining for decoder-only LLMs and robust threshold optimization, contributing new methods for disinformation detection in low-resource languages.</abstract>
    <identifier type="citekey">bazdyrev-etal-2025-transforming</identifier>
    <identifier type="doi">10.18653/v1/2025.unlp-1.13</identifier>
    <location>
        <url>https://aclanthology.org/2025.unlp-1.13/</url>
    </location>
    <part>
        <date>2025-07</date>
        <extent unit="page">
            <start>112</start>
            <end>119</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Transforming Causal LLM into MLM Encoder for Detecting Social Media Manipulation in Telegram
%A Bazdyrev, Anton
%A Bashtovyi, Ivan
%A Havlytskyi, Ivan
%A Kharytonov, Oleksandr
%A Khodakovskyi, Artur
%Y Romanyshyn, Mariana
%S Proceedings of the Fourth Ukrainian Natural Language Processing Workshop (UNLP 2025)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria (online)
%@ 979-8-89176-269-5
%F bazdyrev-etal-2025-transforming
%X We participated in the Fourth UNLP shared task on detecting social media manipulation in Ukrainian Telegram posts, addressing both multilabel technique classification and token-level span identification. We propose two complementary solutions: for classification, we fine-tune the decoder-only model with class-balanced grid-search thresholding and ensembling. For span detection, we convert causal LLM into a bidirectional encoder via masked language modeling pretraining on large Ukrainian and Russian news corpora before fine-tuning. Our solutions achieve SOTA metric results on both shared task track. Our work demonstrates the efficacy of bidirectional pretraining for decoder-only LLMs and robust threshold optimization, contributing new methods for disinformation detection in low-resource languages.
%R 10.18653/v1/2025.unlp-1.13
%U https://aclanthology.org/2025.unlp-1.13/
%U https://doi.org/10.18653/v1/2025.unlp-1.13
%P 112-119

Markdown (Informal)

[Transforming Causal LLM into MLM Encoder for Detecting Social Media Manipulation in Telegram](https://aclanthology.org/2025.unlp-1.13/) (Bazdyrev et al., UNLP 2025)

• Transforming Causal LLM into MLM Encoder for Detecting Social Media Manipulation in Telegram (Bazdyrev et al., UNLP 2025)

ACL

• Anton Bazdyrev, Ivan Bashtovyi, Ivan Havlytskyi, Oleksandr Kharytonov, and Artur Khodakovskyi. 2025. Transforming Causal LLM into MLM Encoder for Detecting Social Media Manipulation in Telegram. In Proceedings of the Fourth Ukrainian Natural Language Processing Workshop (UNLP 2025), pages 112–119, Vienna, Austria (online). Association for Computational Linguistics.