Probabilistic Concept Graph Reasoning for Multimodal Misinformation Detection

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yang, Ruichao, Gao, Wei, Zhu, Xiaobin, Ma, Jing, Lin, Hongzhan, Luo, Ziyang, Zhang, Bo-Wen, Yin, Xu-Cheng
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911546055065600
author Yang, Ruichao
Gao, Wei
Zhu, Xiaobin
Ma, Jing
Lin, Hongzhan
Luo, Ziyang
Zhang, Bo-Wen
Yin, Xu-Cheng
author_facet Yang, Ruichao
Gao, Wei
Zhu, Xiaobin
Ma, Jing
Lin, Hongzhan
Luo, Ziyang
Zhang, Bo-Wen
Yin, Xu-Cheng
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2603_25203
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Probabilistic Concept Graph Reasoning for Multimodal Misinformation Detection
Yang, Ruichao
Gao, Wei
Zhu, Xiaobin
Ma, Jing
Lin, Hongzhan
Luo, Ziyang
Zhang, Bo-Wen
Yin, Xu-Cheng
Computer Vision and Pattern Recognition
Computation and Language
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.
title Probabilistic Concept Graph Reasoning for Multimodal Misinformation Detection
topic Computer Vision and Pattern Recognition
Computation and Language
url https://arxiv.org/abs/2603.25203