@inproceedings{tong-etal-2026-cognidir,
title = "{C}ogni{D}ir: Combating Cognitive Malicious Comments via Adaptive Distributional Learning for Robust Fake News Detection",
author = "Tong, Zhao and
Gong, Chunlin and
Gu, Yimeng and
Shi, Haichao and
Liu, Qiang and
Wu, Shu and
Xu, Xingcheng and
Zhang, Xiao-Yu",
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.655/",
pages = "15050--15067",
ISBN = "979-8-89176-459-0",
abstract = "The proliferation of large language models (LLMs) has enabled a new class of psychologically grounded malicious comments, shifting fake news attacks from surface-level textual noise to deep cognitive and logical manipulation. This shift severely undermines existing detectors, which conventionally rely on static attack assumptions and fixed training distributions. To bridge this gap, we introduce CogniDir, an adaptive distributional learning framework that reformulates robust detection as a dynamic, optimal data mixture optimization problem for social media content safety. Grounded in cognitive psychology, we first formalize mechanism-specific cognitive adversarial paradigms to systematically expose deep-seated detector vulnerabilities. To address the vulnerability heterogeneity, CogniDir derives an information-theoretic score coupling empirical accuracy with probabilistic confidence, which is then parameterized into a Dirichlet prior. This formulation enables smooth, feedback-driven reallocation of training exposure, mathematically guaranteeing the optimal data mixture ratio toward the most brittle attack mechanisms. Experimental results on three benchmarks demonstrate that CogniDir yields state-of-the-art robustness, improving F1 scores by up to 17.9{\%} over competitive baselines under heterogeneous, AI-generated adversarial pressures."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tong-etal-2026-cognidir">
<titleInfo>
<title>CogniDir: Combating Cognitive Malicious Comments via Adaptive Distributional Learning for Robust Fake News Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhao</namePart>
<namePart type="family">Tong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chunlin</namePart>
<namePart type="family">Gong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yimeng</namePart>
<namePart type="family">Gu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haichao</namePart>
<namePart type="family">Shi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qiang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shu</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xingcheng</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiao-Yu</namePart>
<namePart type="family">Zhang</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>The proliferation of large language models (LLMs) has enabled a new class of psychologically grounded malicious comments, shifting fake news attacks from surface-level textual noise to deep cognitive and logical manipulation. This shift severely undermines existing detectors, which conventionally rely on static attack assumptions and fixed training distributions. To bridge this gap, we introduce CogniDir, an adaptive distributional learning framework that reformulates robust detection as a dynamic, optimal data mixture optimization problem for social media content safety. Grounded in cognitive psychology, we first formalize mechanism-specific cognitive adversarial paradigms to systematically expose deep-seated detector vulnerabilities. To address the vulnerability heterogeneity, CogniDir derives an information-theoretic score coupling empirical accuracy with probabilistic confidence, which is then parameterized into a Dirichlet prior. This formulation enables smooth, feedback-driven reallocation of training exposure, mathematically guaranteeing the optimal data mixture ratio toward the most brittle attack mechanisms. Experimental results on three benchmarks demonstrate that CogniDir yields state-of-the-art robustness, improving F1 scores by up to 17.9% over competitive baselines under heterogeneous, AI-generated adversarial pressures.</abstract>
<identifier type="citekey">tong-etal-2026-cognidir</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.655/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>15050</start>
<end>15067</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CogniDir: Combating Cognitive Malicious Comments via Adaptive Distributional Learning for Robust Fake News Detection
%A Tong, Zhao
%A Gong, Chunlin
%A Gu, Yimeng
%A Shi, Haichao
%A Liu, Qiang
%A Wu, Shu
%A Xu, Xingcheng
%A Zhang, Xiao-Yu
%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 tong-etal-2026-cognidir
%X The proliferation of large language models (LLMs) has enabled a new class of psychologically grounded malicious comments, shifting fake news attacks from surface-level textual noise to deep cognitive and logical manipulation. This shift severely undermines existing detectors, which conventionally rely on static attack assumptions and fixed training distributions. To bridge this gap, we introduce CogniDir, an adaptive distributional learning framework that reformulates robust detection as a dynamic, optimal data mixture optimization problem for social media content safety. Grounded in cognitive psychology, we first formalize mechanism-specific cognitive adversarial paradigms to systematically expose deep-seated detector vulnerabilities. To address the vulnerability heterogeneity, CogniDir derives an information-theoretic score coupling empirical accuracy with probabilistic confidence, which is then parameterized into a Dirichlet prior. This formulation enables smooth, feedback-driven reallocation of training exposure, mathematically guaranteeing the optimal data mixture ratio toward the most brittle attack mechanisms. Experimental results on three benchmarks demonstrate that CogniDir yields state-of-the-art robustness, improving F1 scores by up to 17.9% over competitive baselines under heterogeneous, AI-generated adversarial pressures.
%U https://aclanthology.org/2026.emnlp-main.655/
%P 15050-15067
Markdown (Informal)
[CogniDir: Combating Cognitive Malicious Comments via Adaptive Distributional Learning for Robust Fake News Detection](https://aclanthology.org/2026.emnlp-main.655/) (Tong et al., EMNLP 2026)
ACL
- Zhao Tong, Chunlin Gong, Yimeng Gu, Haichao Shi, Qiang Liu, Shu Wu, Xingcheng Xu, and Xiao-Yu Zhang. 2026. CogniDir: Combating Cognitive Malicious Comments via Adaptive Distributional Learning for Robust Fake News Detection. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 15050–15067, Budapest, Hungary. Association for Computational Linguistics.