How transformer-based models can help combat the global proliferation of misinformation: a system that scalably identifies, tracks, and analyzes the spread of misinformation across thousands of international news websites. Using multilingual Matryoshka embeddings and hierarchical level-wise clustering, it surfaces individual news stories, topics, and overarching themes; multilingual stance detection, natural language inference, and network analysis then assess bias and factual inconsistency to identify outlets that disseminate propaganda.