# UNITE-FND: Reframing Multimodal Fake News Detection through Unimodal Scene Translation

arXiv: https://arxiv.org/abs/2502.11132 · HTML: https://mlsanity.com/paper/2502.11132/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 26 references that are in the map.
- First posted on arXiv 16 Feb 2025.

## Builds on (most cited first, 7 of 7)

- [CAFE: Catastrophic Data Leakage in Vertical Federated Learning](https://mlsanity.com/paper/2110.15122/) (2021)
- [Multimodal Fake News Detection via CLIP-Guided Learning](https://mlsanity.com/paper/2205.14304/) (2022)
- [Each Fake News is Fake in its Own Way: An Attribution Multi-Granularity Benchmark for Multimodal Fake News Detection](https://mlsanity.com/paper/2412.14686/) (2024)
- [MMCFND: Multimodal Multilingual Caption-aware Fake News Detection for Low-resource Indic Languages](https://mlsanity.com/paper/2410.10407/) (2024)
- [AMPLE: Emotion-Aware Multimodal Fusion Prompt Learning for Fake News Detection](https://mlsanity.com/paper/2410.15591/) (2024)
- [A Multimodal Adaptive Graph-based Intelligent Classification Model for Fake News](https://mlsanity.com/paper/2411.06097/) (2024)
- [CroMe: Multimodal Fake News Detection using Cross-Modal Tri-Transformer and Metric Learning](https://mlsanity.com/paper/2501.12422/) (2025)

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

- [The Paradigm Shift: A Comprehensive Survey on Large Vision Language Models for Multimodal Fake News Detection](https://mlsanity.com/paper/2601.15316/) (2026)

## Abstract (arXiv)

Multimodal fake news detection typically demands complex architectures and substantial computational resources, posing deployment challenges in real-world settings. We introduce UNITE-FND, a novel framework that reframes multimodal fake news detection as a unimodal text classification task. We propose six specialized prompting strategies with Gemini 1.5 Pro, converting visual content into structured textual descriptions, and enabling efficient text-only models to preserve critical visual information. To benchmark our approach, we introduce Uni-Fakeddit-55k, a curated dataset family of 55,000 samples each, each processed through our multimodal-to-unimodal translation framework. Experimental results demonstrate that UNITE-FND achieves 92.52% accuracy in binary classification, surpassing prior multimodal models while reducing computational costs by over 10x (TinyBERT variant: 14.5M parameters vs. 250M+ in SOTA models). Additionally, we propose a comprehensive suite of five novel metrics to evaluate image-to-text conversion quality, ensuring optimal information preservation. Our results demonstrate that structured text-based representations can replace direct multimodal processing with minimal loss of accuracy, making UNITE-FND a practical and scalable alternative for resource-constrained environments.