@inproceedings{peng-etal-2026-fake,
title = "Fake News Court: A Multi-Agent Adversarial Framework for Robust Detection of {LLM}-Generated Fake News",
author = "Peng, Mengyao and
Gu, Hongyan and
Ma, Yiping and
Hu, Shiyu and
Huang, Xinli",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-main.2022/",
pages = "46053--46063",
ISBN = "979-8-89176-459-0",
abstract = "Large language models (LLMs) have achieved remarkable success across many domains, yet their generative capabilities have been misused to produce highly realistic fake news that threatens social stability. However, the main existing detection methods, including small language model (SLM)-based approaches and LLM-based detectors, exhibit substantial performance degradation on LLM-generated content, reflecting a lack of robustness. SLM-based detectors rely heavily on fixed data distributions and shallow textual cues, while LLM-based detectors depend on prompt-based inference, making them sensitive to prompting and vulnerable to LLM hallucinations. To address this challenge, we propose Fake News Court (FNC), a robust multi-agent adversarial framework that integrates the complementary strengths of LLM and SLM for detecting LLM-generated fake news. FNC adopts an adversarial learning paradigm in which a quality-controlled generator produces diverse and challenging fake news, while a hybrid detector combines multi-dimensional LLM-based agent reasoning with an SLM-based classifier to ensure stable decisions. Extensive experiments show that FNC achieves an overall accuracy improvement of approximately 6{\%} over competitive baselines on LLM-generated fake news, confirming its robustness."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="peng-etal-2026-fake">
<titleInfo>
<title>Fake News Court: A Multi-Agent Adversarial Framework for Robust Detection of LLM-Generated Fake News</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mengyao</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hongyan</namePart>
<namePart type="family">Gu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yiping</namePart>
<namePart type="family">Ma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shiyu</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xinli</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-459-0</identifier>
</relatedItem>
<abstract>Large language models (LLMs) have achieved remarkable success across many domains, yet their generative capabilities have been misused to produce highly realistic fake news that threatens social stability. However, the main existing detection methods, including small language model (SLM)-based approaches and LLM-based detectors, exhibit substantial performance degradation on LLM-generated content, reflecting a lack of robustness. SLM-based detectors rely heavily on fixed data distributions and shallow textual cues, while LLM-based detectors depend on prompt-based inference, making them sensitive to prompting and vulnerable to LLM hallucinations. To address this challenge, we propose Fake News Court (FNC), a robust multi-agent adversarial framework that integrates the complementary strengths of LLM and SLM for detecting LLM-generated fake news. FNC adopts an adversarial learning paradigm in which a quality-controlled generator produces diverse and challenging fake news, while a hybrid detector combines multi-dimensional LLM-based agent reasoning with an SLM-based classifier to ensure stable decisions. Extensive experiments show that FNC achieves an overall accuracy improvement of approximately 6% over competitive baselines on LLM-generated fake news, confirming its robustness.</abstract>
<identifier type="citekey">peng-etal-2026-fake</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.2022/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>46053</start>
<end>46063</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Fake News Court: A Multi-Agent Adversarial Framework for Robust Detection of LLM-Generated Fake News
%A Peng, Mengyao
%A Gu, Hongyan
%A Ma, Yiping
%A Hu, Shiyu
%A Huang, Xinli
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F peng-etal-2026-fake
%X Large language models (LLMs) have achieved remarkable success across many domains, yet their generative capabilities have been misused to produce highly realistic fake news that threatens social stability. However, the main existing detection methods, including small language model (SLM)-based approaches and LLM-based detectors, exhibit substantial performance degradation on LLM-generated content, reflecting a lack of robustness. SLM-based detectors rely heavily on fixed data distributions and shallow textual cues, while LLM-based detectors depend on prompt-based inference, making them sensitive to prompting and vulnerable to LLM hallucinations. To address this challenge, we propose Fake News Court (FNC), a robust multi-agent adversarial framework that integrates the complementary strengths of LLM and SLM for detecting LLM-generated fake news. FNC adopts an adversarial learning paradigm in which a quality-controlled generator produces diverse and challenging fake news, while a hybrid detector combines multi-dimensional LLM-based agent reasoning with an SLM-based classifier to ensure stable decisions. Extensive experiments show that FNC achieves an overall accuracy improvement of approximately 6% over competitive baselines on LLM-generated fake news, confirming its robustness.
%U https://aclanthology.org/2026.emnlp-main.2022/
%P 46053-46063
Markdown (Informal)
[Fake News Court: A Multi-Agent Adversarial Framework for Robust Detection of LLM-Generated Fake News](https://aclanthology.org/2026.emnlp-main.2022/) (Peng et al., EMNLP 2026)
ACL