Work

MultiReflect: Multimodal Self-Reflective RAG-based Automated Fact-Checking

Year: 2025

Type: conference-paper

Abstract: In this work, we introduce MultiReflect, a novel multimodal self-reflective Retrieval Augmented Generation (RAG)-based automated fact-checking pipeline.MultiReflect is designed to address the challenges of rapidly outdated information, limitations in human query capabilities, and expert knowledge barriers in fact-checking.Our proposed pipeline leverages the latest advancements in Large Language Models (LLMs) and Retrieval Augmented Generation (RAG) to enhance fact verification across text and images.Specifically, by integrating multimodal data processing with RAG-based evidence reflection, our system improves the accuracy of fact-checking by utilizing internet-sourced verification.We evaluate our results on the VERITE benchmarks and using several multimodal LLMs, outperforming baselines in binary classification. 1

DOI: 10.18653/v1/2025.magmar-1.1

Authors: Uku Kangur, Krish Agrawal, Yashashvi Singh, Ahmed Sabir, Rajesh Sharma

Institutions: University of Tartu, Indian Institute of Technology Indore, Indian Institute of Information Technology Dharwad, Plaksha University

Language: English

Topic: Misinformation and Its Impacts

Subfield: Sociology and Political Science

Field: Social Sciences

Domain: Social Sciences

Open Access status: gold

Funders: Eesti Teadusagentuur, Horizon 2020 Framework Programme, CHIST-ERA

Awards: G1097210012, G495187929, G5168820832, G68222682, G899169222

OpenAlex ID: W4412944252