Multimodal Misinformation Detection by Learning from Synthetic Data with Multimodal LLMs

TL;DR

This paper introduces a method for improving multimodal misinformation detection by selecting synthetic data that closely matches real-world data distributions, significantly enhancing the performance of small multimodal LLMs.

Contribution

The authors propose two model-agnostic data selection techniques to bridge the distribution gap between synthetic and real-world data for misinformation detection.

Findings

Enhanced detection accuracy on real-world datasets

Small MLLMs outperform GPT-4V after data selection

Effective synthetic data utilization for misinformation detection

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~\cite{GPT-4V}.