面向多模态虚假信息检测的概率概念图推理
Probabilistic Concept Graph Reasoning for Multimodal Misinformation Detection
把多模态虚假信息检测重构为「概念图构建 + 图上的层次化注意力推理」，并用 MLLM 自动发现与验证高层概念节点，这条「先建图后推理」的范式可迁移到需要可解释证据链的图文一致性判断任务（如图文匹配、事实核查、caption 幻觉检测）。
原文依据 applies hierarchical attention over this concept graph to infer claim veracity
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论多模态虚假信息带来的挑战日益严峻，传统检测器往往难以应对：它们是不透明的黑箱，面对新的操纵手法时十分脆弱。本文提出概率概念图推理（PCGR），一个可解释、模块化且可演进的框架，将多模态虚假信息检测（MMD）重构为基于概念的结构化推理。PCGR 遵循「先构建、后推理」的范式：首先构建由人类可理解的概念节点组成的图，其中包含由多模态大语言模型（MLLM）自动发现并验证的新型高层概念；随后在该概念图上施加层次化注意力，以推断声明的真实性。该设计产生连接证据与结论的可解释推理链。实验表明，PCGR 达到了最优的 MMD 准确率，并对新出现的操纵类型具有鲁棒性，在粗粒度检测与细粒度操纵识别两方面均优于此前方法。
英文原文摘要 997 字符
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, modular, and evolvable framework that reframes multimodal misinformation detection (MMD) as structured, 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.