ReMMD：用于多模态虚假信息检测的现实化多语言多图像智能验证系统
ReMMD: Realistic Multilingual Multi-Image Agentic Verification for Multimodal Misinformation Detection
摘要
多模态虚假信息检测越来越重要，因为那些具有传播性的帖子通常包含长篇幅的多语言内容、多张图片、不同的来源信息以及复杂的文本与图像组合结构——这些都属于“图像框架错误”的范畴。现有的评估基准和方法仍然无法有效应对这种复杂情况：它们通常只关注简短的标题、单张图片、二元标签或单一来源的信息，而基于智能代理的验证方式在实际证据搜索场景下则成本较高。我们提出了ReMMD这一用于多模态虚假信息检测的实用型多语言多图像智能代理验证框架。ReMMD包含ReMMDBench这个真实场景下的多模态虚假信息检测评估基准，该基准包含500个样本、2,756张图片、五种单一语言的数据、两种跨语言场景、三种文本长度级别、多张图像内容、五种真实性标签、八种失真类型、证据来源信息以及相关解释说明。此外，还包含ReMMD-Agent这一持久记忆型验证工具，它能够将帖子分解为多个基本单元，构建可重复使用的证据集，并预测出结构化的L1/L2/L3类型结果。在各种专有系统、开源LVLM、MMD-Agent和T2-Agent系统中，ReMMD-Agent取得了最佳的五维度真实性评估成绩：使用GPT-5.2时，其准确率为41.80%，宏观F1值为39.12%；同时，其成本比MMD-Agent降低了17.5%，比T2-Agent降低了79.9%。该项目可在https://dang-ai.github.io/ReMMD获取。
English Abstract
Multimodal misinformation detection is increasingly important because viral posts now combine long multilingual narratives, several images, mixed provenance, and subtle text--image framing errors. Existing benchmarks and methods remain poorly matched to this setting: they usually isolate short captions, single images, binary labels, or one manipulation source, while agentic verification remains costly under realistic evidence search. We present ReMMD, a realistic multilingual multi-image agentic verification framework for multimodal misinformation detection. ReMMD includes ReMMDBench, a real-world multimodal misinformation detection benchmark with 500 samples, 2,756 images, five monolingual languages, two cross-lingual settings, three text-length tiers, multi-image posts, five-way veracity labels, eight distortion labels, evidence provenance, and rationales. It also includes ReMMD-Agent, a persistent-memory verifier that decomposes posts into atomic points, builds a reusable evidence set, and predicts structured L1/L2/L3 outputs. Across proprietary systems, open LVLMs, MMD-Agent, and T2-Agent, ReMMD-Agent obtains the best five-way veracity performance, with 41.80% accuracy and 39.12% macro-F1 using GPT-5.2, while reducing cost by 17.5% relative to MMD-Agent and 79.9% relative to T2-Agent. The project is available at https://dang-ai.github.io/ReMMD.