The escalating challenge of misinformation, particularly in political discourse, requires advanced fact-checking solutions; this is even clearer in the more complex scenario of multimodal claims. We tackle this issue using a multimodal large language model in conjunction with retrieval-augmented generation (RAG), and introduce two novel reasoning techniques: Chain of RAG (CoRAG) and Tree of RAG (ToRAG). They fact-check multimodal claims by extracting both textual and image content, retrieving external information, and reasoning subsequent questions to be answered based on prior evidence. We achieve a weighted F1-score of 0.85, surpassing a baseline reasoning technique by 0.14 points. Human evaluation confirms that the vast majority of our generated fact-check explanations contain all information from gold standard data.
@article{arxiv.2404.12065,
title = {RAGAR, Your Falsehood Radar: RAG-Augmented Reasoning for Political Fact-Checking using Multimodal Large Language Models},
author = {M. Abdul Khaliq and P. Chang and M. Ma and B. Pflugfelder and F. Miletić},
journal= {arXiv preprint arXiv:2404.12065},
year = {2024}
}
Comments
8 pages, submitted to ACL Rolling Review June 2024