VeritasAI Multi Agent Framework for Explainable Fake News Detection Using Retrieval Augmented Generation
Abstract
Abstract The spread of misinformation through the internet has become a serious problem forpublic discussion, democracy, and social relations. Most current automated fact-checkingsystems provide users with uninformative single-label verdicts lacking transparencyand explanations, which decreases their usefulness. In this paper, we introduce VeritasAI - an explainable multi-agent system that detects fake news in real-time using Retri-val-Augmented Generation (RAG) and storing knowledge in graphs. VeritasAI consists ofthree specialized large language model agents: the Prosecutor, the Defender, and the Judge.These agents rely on evidence obtained by semantic search through web and news pagesbased on FAISS vector ranking. VeritasAI produces structured verdicts (\texttt{TRUE}, \texttt{FALSE},\texttt{MISLEADING}, or \texttt{UNVERIFIED}), calculates confidence scores, generates evidence-based reasoning points, and provides balanced adversarial arguments for each claim. A Reactfrontend visualizes the entire verification pipeline, including progress indicators,evidence cards, and claim statistics. Experimental evaluation shows competitive de-tection performance with significantly higher explainability metrics compared to black-box baselines. The system is freely available at https://github.com/Sandarsh18/VeritasAI.
Read the paper
Related studies
- Knowledge Management Perspective of Generative Artificial Intelligence
- Navigating Generative Artificial Intelligence Promises and Perils for Knowledge and Creative Work
- Characterizing the evolving research on enterprise content management
- Large language models and multimodal foundation models for precision oncology
- From Generative AI to Extended Reality: Multidisciplinary Perspectives on the Challenges, Opportunities, and Future of Educational Computing
- Generative Artificial Intelligence: A New Engine for Advancing Environmental Science and Engineering
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.