FinVet: A Collaborative Framework of RAG and External Fact-Checking Agents for Financial Misinformation Detection
This addresses the threat of financial misinformation that can cause billions in losses, providing a more transparent and evidence-backed solution, though it appears incremental as it builds on existing RAG and fact-checking methods.
The paper tackles the problem of detecting financial misinformation by introducing FinVet, a multi-agent framework that integrates RAG pipelines with external fact-checking, achieving an F1 score of 0.85, which is a 10.4% improvement over the best individual pipeline and 37% improvement over standalone RAG approaches.
Financial markets face growing threats from misinformation that can trigger billions in losses in minutes. Most existing approaches lack transparency in their decision-making and provide limited attribution to credible sources. We introduce FinVet, a novel multi-agent framework that integrates two Retrieval-Augmented Generation (RAG) pipelines with external fact-checking through a confidence-weighted voting mechanism. FinVet employs adaptive three-tier processing that dynamically adjusts verification strategies based on retrieval confidence, from direct metadata extraction to hybrid reasoning to full model-based analysis. Unlike existing methods, FinVet provides evidence-backed verdicts, source attribution, confidence scores, and explicit uncertainty flags when evidence is insufficient. Experimental evaluation on the FinFact dataset shows that FinVet achieves an F1 score of 0.85, which is a 10.4% improvement over the best individual pipeline (fact-check pipeline) and 37% improvement over standalone RAG approaches.