Probabilistic Concept Graph Reasoning for Multimodal Misinformation Detection
This addresses the escalating challenge of multimodal misinformation for social media platforms and fact-checkers, offering an interpretable and evolvable solution.
The paper tackles multimodal misinformation detection by proposing Probabilistic Concept Graph Reasoning (PCGR), which reframes detection as concept-based reasoning using automatically discovered high-level concepts; experiments show it achieves state-of-the-art accuracy and robustness, outperforming prior methods.
Multimodal misinformation poses an escalating challenge that often evades traditional detectors, which are opaque black boxes and fragile against new manipulation tactics. We present Probabilistic Concept Graph Reasoning (PCGR), an interpretable and evolvable framework that reframes multimodal misinformation detection (MMD) as structured and concept-based reasoning. PCGR follows a build-then-infer paradigm, which first constructs a graph of human-understandable concept nodes, including novel high-level concepts automatically discovered and validated by multimodal large language models (MLLMs), and then applies hierarchical attention over this concept graph to infer claim veracity. This design produces interpretable reasoning chains linking evidence to conclusions. Experiments demonstrate that PCGR achieves state-of-the-art MMD accuracy and robustness to emerging manipulation types, outperforming prior methods in both coarse detection and fine-grained manipulation recognition.