@inproceedings{nguyen-son-etal-2024-simllm,
title = "{S}im{LLM}: Detecting Sentences Generated by Large Language Models Using Similarity between the Generation and its Re-generation",
author = "Nguyen-Son, Hoang-Quoc and
Dao, Minh-Son and
Zettsu, Koji",
editor = "Al-Onaizan, Yaser and
Bansal, Mohit and
Chen, Yun-Nung",
booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.emnlp-main.1246",
pages = "22340--22352",
abstract = "Large language models have emerged as a significant phenomenon due to their ability to produce natural text across various applications. However, the proliferation of generated text raises concerns regarding its potential misuse in fraudulent activities such as academic dishonesty, spam dissemination, and misinformation propagation. Prior studies have detected the generation of non-analogous text, which manifests numerous differences between original and generated text. We have observed that the similarity between the original text and its generation is notably higher than that between the generated text and its subsequent regeneration. To address this, we propose a novel approach named SimLLM, aimed at estimating the similarity between an input sentence and its generated counterpart to detect analogous machine-generated sentences that closely mimic human-written ones. Our empirical analysis demonstrates SimLLM{'}s superior performance compared to existing methods.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nguyen-son-etal-2024-simllm">
<titleInfo>
<title>SimLLM: Detecting Sentences Generated by Large Language Models Using Similarity between the Generation and its Re-generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hoang-Quoc</namePart>
<namePart type="family">Nguyen-Son</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minh-Son</namePart>
<namePart type="family">Dao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Koji</namePart>
<namePart type="family">Zettsu</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>Large language models have emerged as a significant phenomenon due to their ability to produce natural text across various applications. However, the proliferation of generated text raises concerns regarding its potential misuse in fraudulent activities such as academic dishonesty, spam dissemination, and misinformation propagation. Prior studies have detected the generation of non-analogous text, which manifests numerous differences between original and generated text. We have observed that the similarity between the original text and its generation is notably higher than that between the generated text and its subsequent regeneration. To address this, we propose a novel approach named SimLLM, aimed at estimating the similarity between an input sentence and its generated counterpart to detect analogous machine-generated sentences that closely mimic human-written ones. Our empirical analysis demonstrates SimLLM’s superior performance compared to existing methods.</abstract>
<identifier type="citekey">nguyen-son-etal-2024-simllm</identifier>
<location>
<url>https://aclanthology.org/2024.emnlp-main.1246</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>22340</start>
<end>22352</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SimLLM: Detecting Sentences Generated by Large Language Models Using Similarity between the Generation and its Re-generation
%A Nguyen-Son, Hoang-Quoc
%A Dao, Minh-Son
%A Zettsu, Koji
%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 nguyen-son-etal-2024-simllm
%X Large language models have emerged as a significant phenomenon due to their ability to produce natural text across various applications. However, the proliferation of generated text raises concerns regarding its potential misuse in fraudulent activities such as academic dishonesty, spam dissemination, and misinformation propagation. Prior studies have detected the generation of non-analogous text, which manifests numerous differences between original and generated text. We have observed that the similarity between the original text and its generation is notably higher than that between the generated text and its subsequent regeneration. To address this, we propose a novel approach named SimLLM, aimed at estimating the similarity between an input sentence and its generated counterpart to detect analogous machine-generated sentences that closely mimic human-written ones. Our empirical analysis demonstrates SimLLM’s superior performance compared to existing methods.
%U https://aclanthology.org/2024.emnlp-main.1246
%P 22340-22352
Markdown (Informal)
[SimLLM: Detecting Sentences Generated by Large Language Models Using Similarity between the Generation and its Re-generation](https://aclanthology.org/2024.emnlp-main.1246) (Nguyen-Son et al., EMNLP 2024)
ACL