<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ma-wang-2024-zero">
    <titleInfo>
        <title>Zero-Shot Detection of LLM-Generated Text using Token Cohesiveness</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Shixuan</namePart>
        <namePart type="family">Ma</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Quan</namePart>
        <namePart type="family">Wang</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>Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing</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>The increasing capability and widespread usage of large language models (LLMs) highlight the desirability of automatic detection of LLM-generated text. Zero-shot detectors, due to their training-free nature, have received considerable attention and notable success. In this paper, we identify a new feature, token cohesiveness, that is useful for zero-shot detection, and we demonstrate that LLM-generated text tends to exhibit higher token cohesiveness than human-written text. Based on this observation, we devise TOCSIN, a generic dual-channel detection paradigm that uses token cohesiveness as a plug-and-play module to improve existing zero-shot detectors. To calculate token cohesiveness, TOCSIN only requires a few rounds of random token deletion and semantic difference measurement, making it particularly suitable for a practical black-box setting where the source model used for generation is not accessible. Extensive experiments with four state-of-the-art base detectors on various datasets, source models, and evaluation settings demonstrate the effectiveness and generality of the proposed approach. Code available at: https://github.com/Shixuan-Ma/TOCSIN.</abstract>
    <identifier type="citekey">ma-wang-2024-zero</identifier>
    <identifier type="doi">10.18653/v1/2024.emnlp-main.971</identifier>
    <location>
        <url>https://aclanthology.org/2024.emnlp-main.971/</url>
    </location>
    <part>
        <date>2024-11</date>
        <extent unit="page">
            <start>17538</start>
            <end>17553</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Zero-Shot Detection of LLM-Generated Text using Token Cohesiveness
%A Ma, Shixuan
%A Wang, Quan
%Y Al-Onaizan, Yaser
%Y Bansal, Mohit
%Y Chen, Yun-Nung
%S Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F ma-wang-2024-zero
%X The increasing capability and widespread usage of large language models (LLMs) highlight the desirability of automatic detection of LLM-generated text. Zero-shot detectors, due to their training-free nature, have received considerable attention and notable success. In this paper, we identify a new feature, token cohesiveness, that is useful for zero-shot detection, and we demonstrate that LLM-generated text tends to exhibit higher token cohesiveness than human-written text. Based on this observation, we devise TOCSIN, a generic dual-channel detection paradigm that uses token cohesiveness as a plug-and-play module to improve existing zero-shot detectors. To calculate token cohesiveness, TOCSIN only requires a few rounds of random token deletion and semantic difference measurement, making it particularly suitable for a practical black-box setting where the source model used for generation is not accessible. Extensive experiments with four state-of-the-art base detectors on various datasets, source models, and evaluation settings demonstrate the effectiveness and generality of the proposed approach. Code available at: https://github.com/Shixuan-Ma/TOCSIN.
%R 10.18653/v1/2024.emnlp-main.971
%U https://aclanthology.org/2024.emnlp-main.971/
%U https://doi.org/10.18653/v1/2024.emnlp-main.971
%P 17538-17553

Markdown (Informal)

[Zero-Shot Detection of LLM-Generated Text using Token Cohesiveness](https://aclanthology.org/2024.emnlp-main.971/) (Ma & Wang, EMNLP 2024)

• Zero-Shot Detection of LLM-Generated Text using Token Cohesiveness (Ma & Wang, EMNLP 2024)

ACL

• Shixuan Ma and Quan Wang. 2024. Zero-Shot Detection of LLM-Generated Text using Token Cohesiveness. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 17538–17553, Miami, Florida, USA. Association for Computational Linguistics.