Fact-Checking With Contextual Narratives

Leveraging Retrieval-Augmented LLMs for Social Media Analysis

Bibliographic Data

ID22107348
AuthorsArka Ujjal Dey (0000-0001-8392-1574, University of Surrey, corresponding author), Muhammad Junaid Awan (0000-0002-3857-1293, University of Surrey), Georgia Channing (0009-0001-6354-7527, University of Oxford), Christian Schroeder de Witt (0000-0003-4245-1179, University of Oxford), John Collomosse (0000-0003-3580-4685, Adobe Research, Adobe Systems Inc., San Jose, CA, USA)
Year2026
Volume13
Issue3
Pages3365-3376
Publication date2026-06-01
Open AccessYes
TypeARTICLE
VenueIEEE Transactions on Computational Social Systems (JOURNAL)
Journal identifiersISSN: 2329-924X • E-ISSN: 2373-7476
PublisherInstitute of Electrical and Electronics Engineers (IEEE) (PUBLISHER)
DOI10.1109/tcss.2026.3669799
OpenAlexW7140293053
LanguageEN
References cited34

Fact-checking systems have gained traction as scalable solutions, yet they often face challenges such as handling diverse evidence sources, integrating multimodal data, and presenting comprehensive narratives. In this work, we propose cluster-based retrieval augmented verification with explanation (CRAVE), a novel framework that integrates retrieval-augmented large language models (LLMs) with clustering techniques to address multimodal misinformation on social media. The framework is designed to process multimodal inputs (text and images) and iteratively refine evidence through agent-based mechanisms. We validated the framework on multiple real-world and synthetic datasets, showing that breaking up evidence into narrative clusters improves both retrieval precision, clustering quality, and judgment accuracy, showcasing its potential as a robust decision-support tool for fact-checkers

Content analysis · Social media · Social network analysis · Computational and Text Analysis Methods · Sentiment Analysis and Opinion Mining · Topic Modeling

Tools

Open DOI