@inproceedings{li-etal-2025-spade,
title = "{SPADE}: Structured Prompting Augmentation for Dialogue Enhancement in Machine-Generated Text Detection",
author = "Li, Haoyi and
Yuan, Angela and
Han, Soyeon and
Leckie, Chirstopher",
editor = "Derczynski, Leon and
Novikova, Jekaterina and
Chen, Muhao",
booktitle = "Proceedings of the The First Workshop on LLM Security (LLMSEC)",
month = aug,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.llmsec-1.11/",
pages = "142--167",
ISBN = "979-8-89176-279-4",
abstract = "The increasing capability of large language models (LLMs) to generate synthetic content has heightened concerns about their misuse, driving the development of Machine-Generated Text (MGT) detection models. However, these detectors face significant challenges due to the lack of high-quality synthetic datasets for training. To address this issue, we propose SPADE, a structured framework for detecting synthetic dialogues using prompt-based adversarial samples. Our proposed methods yield 14 new dialogue datasets, which we benchmark against eight MGT detection models. The results demonstrate improved generalization performance when utilizing a mixed dataset produced by proposed augmentation frameworks, offering a practical approach to enhancing LLM application security. Considering that real-world agents lack knowledge of future opponent utterances, we simulate online dialogue detection and examine the relationship between chat history length and detection accuracy. Our open-source datasets can be downloaded."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2025-spade">
<titleInfo>
<title>SPADE: Structured Prompting Augmentation for Dialogue Enhancement in Machine-Generated Text Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Haoyi</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Angela</namePart>
<namePart type="family">Yuan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Soyeon</namePart>
<namePart type="family">Han</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chirstopher</namePart>
<namePart type="family">Leckie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the The First Workshop on LLM Security (LLMSEC)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Leon</namePart>
<namePart type="family">Derczynski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jekaterina</namePart>
<namePart type="family">Novikova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Muhao</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">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-279-4</identifier>
</relatedItem>
<abstract>The increasing capability of large language models (LLMs) to generate synthetic content has heightened concerns about their misuse, driving the development of Machine-Generated Text (MGT) detection models. However, these detectors face significant challenges due to the lack of high-quality synthetic datasets for training. To address this issue, we propose SPADE, a structured framework for detecting synthetic dialogues using prompt-based adversarial samples. Our proposed methods yield 14 new dialogue datasets, which we benchmark against eight MGT detection models. The results demonstrate improved generalization performance when utilizing a mixed dataset produced by proposed augmentation frameworks, offering a practical approach to enhancing LLM application security. Considering that real-world agents lack knowledge of future opponent utterances, we simulate online dialogue detection and examine the relationship between chat history length and detection accuracy. Our open-source datasets can be downloaded.</abstract>
<identifier type="citekey">li-etal-2025-spade</identifier>
<location>
<url>https://aclanthology.org/2025.llmsec-1.11/</url>
</location>
<part>
<date>2025-08</date>
<extent unit="page">
<start>142</start>
<end>167</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SPADE: Structured Prompting Augmentation for Dialogue Enhancement in Machine-Generated Text Detection
%A Li, Haoyi
%A Yuan, Angela
%A Han, Soyeon
%A Leckie, Chirstopher
%Y Derczynski, Leon
%Y Novikova, Jekaterina
%Y Chen, Muhao
%S Proceedings of the The First Workshop on LLM Security (LLMSEC)
%D 2025
%8 August
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-279-4
%F li-etal-2025-spade
%X The increasing capability of large language models (LLMs) to generate synthetic content has heightened concerns about their misuse, driving the development of Machine-Generated Text (MGT) detection models. However, these detectors face significant challenges due to the lack of high-quality synthetic datasets for training. To address this issue, we propose SPADE, a structured framework for detecting synthetic dialogues using prompt-based adversarial samples. Our proposed methods yield 14 new dialogue datasets, which we benchmark against eight MGT detection models. The results demonstrate improved generalization performance when utilizing a mixed dataset produced by proposed augmentation frameworks, offering a practical approach to enhancing LLM application security. Considering that real-world agents lack knowledge of future opponent utterances, we simulate online dialogue detection and examine the relationship between chat history length and detection accuracy. Our open-source datasets can be downloaded.
%U https://aclanthology.org/2025.llmsec-1.11/
%P 142-167
Markdown (Informal)
[SPADE: Structured Prompting Augmentation for Dialogue Enhancement in Machine-Generated Text Detection](https://aclanthology.org/2025.llmsec-1.11/) (Li et al., LLMSEC 2025)
ACL