@inproceedings{keles-etal-2025-know,
title = "{I} Know You Did Not Write That! A Sampling Based Watermarking Method for Identifying Machine Generated Text",
author = {Kele{\c{s}}, Kaan Efe and
G{\"u}rb{\"u}z, {\"O}mer Kaan and
Kutlu, Mucahid},
editor = "Alam, Firoj and
Nakov, Preslav and
Habash, Nizar and
Gurevych, Iryna and
Chowdhury, Shammur and
Shelmanov, Artem and
Wang, Yuxia and
Artemova, Ekaterina and
Kutlu, Mucahid and
Mikros, George",
booktitle = "Proceedings of the 1stWorkshop on GenAI Content Detection (GenAIDetect)",
month = jan,
year = "2025",
address = "Abu Dhabi, UAE",
publisher = "International Conference on Computational Linguistics",
url = "https://aclanthology.org/2025.genaidetect-1.11/",
pages = "140--149",
abstract = "Potential harms of Large Language Models such as mass misinformation and plagiarism can be partially mitigated if there exists a reliable way to detect machine generated text. In this paper, we propose a new watermarking method to detect machine-generated texts. Our method embeds a unique pattern within the generated text, ensuring that while the content remains coherent and natural to human readers, it carries distinct markers that can be identified algorithmically. Specifically, we intervene with the token sampling process in a way which enables us to trace back our token choices during the detection phase. We show how watermarking affects textual quality and compare our proposed method with a state-of-the-art watermarking method in terms of robustness and detectability. Through extensive experiments, we demonstrate the effectiveness of our watermarking scheme in distinguishing between watermarked and non-watermarked text, achieving high detection rates while maintaining textual quality."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="keles-etal-2025-know">
<titleInfo>
<title>I Know You Did Not Write That! A Sampling Based Watermarking Method for Identifying Machine Generated Text</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kaan</namePart>
<namePart type="given">Efe</namePart>
<namePart type="family">Keleş</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ömer</namePart>
<namePart type="given">Kaan</namePart>
<namePart type="family">Gürbüz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mucahid</namePart>
<namePart type="family">Kutlu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-01</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 1stWorkshop on GenAI Content Detection (GenAIDetect)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Firoj</namePart>
<namePart type="family">Alam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preslav</namePart>
<namePart type="family">Nakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nizar</namePart>
<namePart type="family">Habash</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iryna</namePart>
<namePart type="family">Gurevych</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shammur</namePart>
<namePart type="family">Chowdhury</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Artem</namePart>
<namePart type="family">Shelmanov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuxia</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Artemova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mucahid</namePart>
<namePart type="family">Kutlu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">George</namePart>
<namePart type="family">Mikros</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Conference on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, UAE</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Potential harms of Large Language Models such as mass misinformation and plagiarism can be partially mitigated if there exists a reliable way to detect machine generated text. In this paper, we propose a new watermarking method to detect machine-generated texts. Our method embeds a unique pattern within the generated text, ensuring that while the content remains coherent and natural to human readers, it carries distinct markers that can be identified algorithmically. Specifically, we intervene with the token sampling process in a way which enables us to trace back our token choices during the detection phase. We show how watermarking affects textual quality and compare our proposed method with a state-of-the-art watermarking method in terms of robustness and detectability. Through extensive experiments, we demonstrate the effectiveness of our watermarking scheme in distinguishing between watermarked and non-watermarked text, achieving high detection rates while maintaining textual quality.</abstract>
<identifier type="citekey">keles-etal-2025-know</identifier>
<location>
<url>https://aclanthology.org/2025.genaidetect-1.11/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>140</start>
<end>149</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T I Know You Did Not Write That! A Sampling Based Watermarking Method for Identifying Machine Generated Text
%A Keleş, Kaan Efe
%A Gürbüz, Ömer Kaan
%A Kutlu, Mucahid
%Y Alam, Firoj
%Y Nakov, Preslav
%Y Habash, Nizar
%Y Gurevych, Iryna
%Y Chowdhury, Shammur
%Y Shelmanov, Artem
%Y Wang, Yuxia
%Y Artemova, Ekaterina
%Y Kutlu, Mucahid
%Y Mikros, George
%S Proceedings of the 1stWorkshop on GenAI Content Detection (GenAIDetect)
%D 2025
%8 January
%I International Conference on Computational Linguistics
%C Abu Dhabi, UAE
%F keles-etal-2025-know
%X Potential harms of Large Language Models such as mass misinformation and plagiarism can be partially mitigated if there exists a reliable way to detect machine generated text. In this paper, we propose a new watermarking method to detect machine-generated texts. Our method embeds a unique pattern within the generated text, ensuring that while the content remains coherent and natural to human readers, it carries distinct markers that can be identified algorithmically. Specifically, we intervene with the token sampling process in a way which enables us to trace back our token choices during the detection phase. We show how watermarking affects textual quality and compare our proposed method with a state-of-the-art watermarking method in terms of robustness and detectability. Through extensive experiments, we demonstrate the effectiveness of our watermarking scheme in distinguishing between watermarked and non-watermarked text, achieving high detection rates while maintaining textual quality.
%U https://aclanthology.org/2025.genaidetect-1.11/
%P 140-149
Markdown (Informal)
[I Know You Did Not Write That! A Sampling Based Watermarking Method for Identifying Machine Generated Text](https://aclanthology.org/2025.genaidetect-1.11/) (Keleş et al., GenAIDetect 2025)
ACL