Probabilistic Concept Graph Reasoning for Multimodal Misinformation Detection

TL;DR

This paper introduces PCGR, a structured, interpretable framework for multimodal misinformation detection that leverages concept graphs and hierarchical attention, achieving state-of-the-art accuracy and robustness.

Contribution

The paper proposes a novel concept graph reasoning framework that automatically discovers high-level concepts and enhances interpretability in multimodal misinformation detection.

Findings

Achieves state-of-the-art accuracy in MMD tasks

Demonstrates robustness against new manipulation tactics

Provides interpretable reasoning chains linking evidence to claims

Abstract

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.