Fact-Checking with Contextual Narratives: Leveraging Retrieval-Augmented LLMs for Social Media Analysis

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Dey, Arka Ujjal, Awan, Muhammad Junaid, Channing, Georgia, de Witt, Christian Schroeder, Collomosse, John
Format:	Preprint
Published:	2025
Subjects:	Multimedia
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

_version_	1866913037564248064
author	Dey, Arka Ujjal Awan, Muhammad Junaid Channing, Georgia de Witt, Christian Schroeder Collomosse, John
author_facet	Dey, Arka Ujjal Awan, Muhammad Junaid Channing, Georgia de Witt, Christian Schroeder Collomosse, John
contents	We propose CRAVE (Cluster-based Retrieval Augmented Verification with Explanation); a novel framework that integrates retrieval-augmented Large Language Models (LLMs) with clustering techniques to address fact-checking challenges on social media. CRAVE automatically retrieves multimodal evidence from diverse, often contradictory, sources. Evidence is clustered into coherent narratives, and evaluated via an LLM-based judge to deliver fact-checking verdicts explained by evidence summaries. By synthesizing evidence from both text and image modalities and incorporating agent-based refinement, CRAVE ensures consistency and diversity in evidence representation. Comprehensive experiments demonstrate CRAVE's efficacy in retrieval precision, clustering quality, and judgment accuracy, showcasing its potential as a robust decision-support tool for fact-checkers.
format	Preprint
id	arxiv_https___arxiv_org_abs_2504_10166
institution	arXiv
publishDate	2025
record_format	arxiv
spellingShingle	Fact-Checking with Contextual Narratives: Leveraging Retrieval-Augmented LLMs for Social Media Analysis Dey, Arka Ujjal Awan, Muhammad Junaid Channing, Georgia de Witt, Christian Schroeder Collomosse, John Multimedia We propose CRAVE (Cluster-based Retrieval Augmented Verification with Explanation); a novel framework that integrates retrieval-augmented Large Language Models (LLMs) with clustering techniques to address fact-checking challenges on social media. CRAVE automatically retrieves multimodal evidence from diverse, often contradictory, sources. Evidence is clustered into coherent narratives, and evaluated via an LLM-based judge to deliver fact-checking verdicts explained by evidence summaries. By synthesizing evidence from both text and image modalities and incorporating agent-based refinement, CRAVE ensures consistency and diversity in evidence representation. Comprehensive experiments demonstrate CRAVE's efficacy in retrieval precision, clustering quality, and judgment accuracy, showcasing its potential as a robust decision-support tool for fact-checkers.
title	Fact-Checking with Contextual Narratives: Leveraging Retrieval-Augmented LLMs for Social Media Analysis
topic	Multimedia
url	https://arxiv.org/abs/2504.10166