<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zahid-etal-2024-multi">
    <titleInfo>
        <title>Multi-Loss Fusion: Angular and Contrastive Integration for Machine-Generated Text Detection</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Iqra</namePart>
        <namePart type="family">Zahid</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yue</namePart>
        <namePart type="family">Chang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Tharindu</namePart>
        <namePart type="family">Madusanka</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Youcheng</namePart>
        <namePart type="family">Sun</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Riza</namePart>
        <namePart type="family">Batista-Navarro</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2024-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: EMNLP 2024</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Yaser</namePart>
            <namePart type="family">Al-Onaizan</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Mohit</namePart>
            <namePart type="family">Bansal</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yun-Nung</namePart>
            <namePart type="family">Chen</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Miami, Florida, USA</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Modern natural language generation (NLG) systems have led to the development of synthetic human-like open-ended texts, posing concerns as to who the original author of a text is. To address such concerns, we introduce DeB-Ang: the utilisation of a custom DeBERTa model with angular loss and contrastive loss functions for effective class separation in neural text classification tasks. We expand the application of this model on binary machine-generated text detection and multi-class neural authorship attribution. We demonstrate improved performance on many benchmark datasets whereby the accuracy for machine-generated text detection was increased by as much as 38.04% across all datasets.</abstract>
    <identifier type="citekey">zahid-etal-2024-multi</identifier>
    <identifier type="doi">10.18653/v1/2024.findings-emnlp.421</identifier>
    <location>
        <url>https://aclanthology.org/2024.findings-emnlp.421/</url>
    </location>
    <part>
        <date>2024-11</date>
        <extent unit="page">
            <start>7189</start>
            <end>7202</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Multi-Loss Fusion: Angular and Contrastive Integration for Machine-Generated Text Detection
%A Zahid, Iqra
%A Chang, Yue
%A Madusanka, Tharindu
%A Sun, Youcheng
%A Batista-Navarro, Riza
%Y Al-Onaizan, Yaser
%Y Bansal, Mohit
%Y Chen, Yun-Nung
%S Findings of the Association for Computational Linguistics: EMNLP 2024
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F zahid-etal-2024-multi
%X Modern natural language generation (NLG) systems have led to the development of synthetic human-like open-ended texts, posing concerns as to who the original author of a text is. To address such concerns, we introduce DeB-Ang: the utilisation of a custom DeBERTa model with angular loss and contrastive loss functions for effective class separation in neural text classification tasks. We expand the application of this model on binary machine-generated text detection and multi-class neural authorship attribution. We demonstrate improved performance on many benchmark datasets whereby the accuracy for machine-generated text detection was increased by as much as 38.04% across all datasets.
%R 10.18653/v1/2024.findings-emnlp.421
%U https://aclanthology.org/2024.findings-emnlp.421/
%U https://doi.org/10.18653/v1/2024.findings-emnlp.421
%P 7189-7202

Markdown (Informal)

[Multi-Loss Fusion: Angular and Contrastive Integration for Machine-Generated Text Detection](https://aclanthology.org/2024.findings-emnlp.421/) (Zahid et al., Findings 2024)

• Multi-Loss Fusion: Angular and Contrastive Integration for Machine-Generated Text Detection (Zahid et al., Findings 2024)

ACL

• Iqra Zahid, Yue Chang, Tharindu Madusanka, Youcheng Sun, and Riza Batista-Navarro. 2024. Multi-Loss Fusion: Angular and Contrastive Integration for Machine-Generated Text Detection. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 7189–7202, Miami, Florida, USA. Association for Computational Linguistics.