Deconstruct, Diagnose, and Deliberate: A Protocol-Adaptive Role-Specific Multi-Agent Framework for Fake News Detection

Zhigan Zhang, Jie Sui


Abstract
The rapid spread of fake news on digital platforms presents significant societal challenges, demanding detection methods capable of addressing intricate manipulation strategies. Existing methods predominantly rely on monolithic verification approaches, which fail to decompose the complex blend of factual inaccuracies, logical fallacies, and propaganda techniques in modern misinformation. To address this gap, we propose PARD, a Protocol-Adaptive Role-Specific multi-agent framework that decomposes verification into factual, logical, and contextual dimensions. PARD dynamically selects the optimal interaction protocol from a library that includes Round-Robin Discussion, Point-Counterpoint Dialogue, and Cross-Examination to tailor the reasoning process for more effective detection. We evaluate PARD with LIAR-RAW+, an extended version of the LIAR-RAW dataset enriched with fine-grained factual, logical, and contextual annotations. Experimental results demonstrate that PARD consistently outperforms baseline methods in both predictive accuracy and explanatory quality, supported by its efficient dynamic governance mechanism
Anthology ID:
2026.findings-acl.1227
Volume:
Findings of the Association for Computational Linguistics: ACL 2026
Month:
July
Year:
2026
Address:
San Diego, California, United States
Editors:
Maria Liakata, Viviane P. Moreira, Jiajun Zhang, David Jurgens
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
24516–24534
Language:
URL:
https://aclanthology.org/2026.findings-acl.1227/
DOI:
10.18653/v1/2026.findings-acl.1227
Bibkey:
Cite (ACL):
Zhigan Zhang and Jie Sui. 2026. Deconstruct, Diagnose, and Deliberate: A Protocol-Adaptive Role-Specific Multi-Agent Framework for Fake News Detection. In Findings of the Association for Computational Linguistics: ACL 2026, pages 24516–24534, San Diego, California, United States. Association for Computational Linguistics.
Cite (Informal):
Deconstruct, Diagnose, and Deliberate: A Protocol-Adaptive Role-Specific Multi-Agent Framework for Fake News Detection (Zhang & Sui, Findings 2026)
Copy Citation:
PDF:
https://aclanthology.org/2026.findings-acl.1227.pdf
Checklist:
 2026.findings-acl.1227.checklist.pdf