Multimodal Misinformation Detection by Learning from Synthetic Data with Multimodal LLMs

2024/09/29 by Fengzhu Zeng, Wenqian Li, Zeng, Fengzhu +5 · 4 citations
Computer Science · Social Sciences · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Misinformation and Its Impacts #Spam and Phishing Detection

paper · pdf · doi:10.48550/arxiv.2409.19656

openalex publication_date 2024/09/29 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Detecting multimodal misinformation, especially in the form of image-text pairs, is crucial. Obtaining large-scale, high-quality real-world fact-checking datasets for training detectors is costly, leading researchers to use synthetic datasets generated by AI technologies. However, the generalizability of detectors trained on synthetic data to real-world scenarios remains unclear due to the distribution gap. To address this, we propose learning from synthetic data for detecting real-world multimodal misinformation through two model-agnostic data selection methods that match synthetic and real-world data distributions. Experiments show that our method enhances the performance of a small MLLM (13B) on real-world fact-checking datasets, enabling it to even surpass GPT-4V~\citeGPT-4V.

Cited by

• From Veracity to Diffusion: Adressing Operational Challenges in Moving From Fake-News Detection to Information Disorders
• Enhancing Multimodal Misinformation Detection by Replaying the Whole Story from Image Modality Perspective
• E-CaTCH: Event-Centric Cross-Modal Attention with Temporal Consistency and Class-Imbalance Handling for Misinformation Detection
• XFacta: Contemporary, Real-World Dataset and Evaluation for Multimodal Misinformation Detection with Multimodal LLMs

Related

• Synthetic Misinformers: Generating and Combating Multimodal Misinformation
• LADLE-MM: Limited Annotation based Detector with Learned Ensembles for Multimodal Misinformation
• MMD-Thinker: Adaptive Multi-Dimensional Thinking for Multimodal Misinformation Detection
• LEMMA: Towards LVLM-Enhanced Multimodal Misinformation Detection with External Knowledge Augmentation
• Multimodal Misinformation Detection using Large Vision-Language Models