RAGAR, Your Falsehood Radar: RAG-Augmented Reasoning for Political Fact-Checking using Multimodal Large Language Models
This addresses the problem of multimodal misinformation in political discourse for fact-checkers, though it appears incremental as it builds on existing RAG and reasoning methods.
The paper tackled political misinformation by fact-checking multimodal claims using a multimodal large language model with retrieval-augmented generation, achieving a weighted F1-score of 0.85, which surpassed a baseline by 0.14 points.
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.