# E-FreeM2: Efficient Training-Free Multi-Scale and Cross-Modal News Verification via MLLMs

arXiv: https://arxiv.org/abs/2506.20944 · HTML: https://mlsanity.com/paper/2506.20944/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Jun 2025.

## Built on by (most cited first, 1 of 1)

- [Multimedia Verification Through Multi-Agent Deep Research Multimodal Large Language Models](https://mlsanity.com/paper/2507.04410/) (2025)

## Abstract (arXiv)

The rapid spread of misinformation in mobile and wireless networks presents critical security challenges. This study introduces a training-free, retrieval-based multimodal fact verification system that leverages pretrained vision-language models and large language models for credibility assessment. By dynamically retrieving and cross-referencing trusted data sources, our approach mitigates vulnerabilities of traditional training-based models, such as adversarial attacks and data poisoning. Additionally, its lightweight design enables seamless edge device integration without extensive on-device processing. Experiments on two fact-checking benchmarks achieve SOTA results, confirming its effectiveness in misinformation detection and its robustness against various attack vectors, highlighting its potential to enhance security in mobile and wireless communication environments.