# Retrieval-Augmented Multimodal Model for Fake News Detection

arXiv: https://arxiv.org/abs/2604.18112 · HTML: https://mlsanity.com/paper/2604.18112/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Multimodal RAG, one of 15 directions in Retrieval-augmented generation.
- Builds on 21 of its 62 references that are in the map.
- First posted on arXiv 20 Apr 2026.

## Placed in

- Retrieval-augmented generation / [Multimodal RAG](https://mlsanity.com/rag/multimodal-rag/)

## Builds on (most cited first, 21 of 21)

- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [SimCSE: Simple Contrastive Learning of Sentence Embeddings](https://mlsanity.com/paper/2104.08821/) (2021)
- [C-Pack: Packed Resources For General Chinese Embeddings](https://mlsanity.com/paper/2309.07597/) (2023)
- [On Variational Bounds of Mutual Information](https://mlsanity.com/paper/1905.06922/) (2019)
- [Information-theoretic analysis of generalization capability of learning algorithms](https://mlsanity.com/paper/1705.07809/) (2017)
- [MDFEND: Multi-domain Fake News Detection](https://mlsanity.com/paper/2201.00987/) (2022)
- [Embracing Domain Differences in Fake News: Cross-domain Fake News Detection using Multi-modal Data](https://mlsanity.com/paper/2102.06314/) (2021)
- [Explainable Fake News Detection With Large Language Model via Defense Among Competing Wisdom](https://mlsanity.com/paper/2405.03371/) (2024)
- [Generalizing to the Future: Mitigating Entity Bias in Fake News Detection](https://mlsanity.com/paper/2204.09484/) (2022)
- [Memory-Guided Multi-View Multi-Domain Fake News Detection](https://mlsanity.com/paper/2206.12808/) (2022)
- [Beyond ReAct: A Planner-Centric Framework for Complex Tool-Augmented LLM Reasoning](https://mlsanity.com/paper/2511.10037/) (2025)
- [Igniting Creative Writing in Small Language Models: LLM-as-a-Judge versus Multi-Agent Refined Rewards](https://mlsanity.com/paper/2508.21476/) (2025)
- [Challenges and Innovations in LLM-Powered Fake News Detection: A Synthesis of Approaches and Future Directions](https://mlsanity.com/paper/2502.00339/) (2025)
- [Is LLMs Hallucination Usable? LLM-based Negative Reasoning for Fake News Detection](https://mlsanity.com/paper/2503.09153/) (2025)
- [FineFake: A Knowledge-Enriched Dataset for Fine-Grained Multi-Domain Fake News Detection](https://mlsanity.com/paper/2404.01336/) (2024)
- [Fake News Detection: Comparative Evaluation of BERT-like Models and Large Language Models with Generative AI-Annotated Data](https://mlsanity.com/paper/2412.14276/) (2024)
- [A Macro- and Micro-Hierarchical Transfer Learning Framework for Cross-Domain Fake News Detection](https://mlsanity.com/paper/2502.14403/) (2025)
- [Diffusion-based Multi-modal Synergy Interest Network for Click-through Rate Prediction](https://mlsanity.com/paper/2508.21460/) (2025)
- [Coherency Improved Explainable Recommendation via Large Language Model](https://mlsanity.com/paper/2504.05315/) (2025)
- [From Manipulation to Mistrust: Explaining Diverse Micro-Video Misinformation for Robust Debunking in the Wild](https://mlsanity.com/paper/2603.25423/) (2026)
- [Unseen Fake News Detection Through Casual Debiasing](https://mlsanity.com/paper/2503.04160/) (2025)

## Abstract (arXiv)

In recent years, multimodal multidomain fake news detection has garnered increasing attention. Nevertheless, this direction presents two significant challenges: (1) Failure to Capture Cross-Instance Narrative Consistency: existing models usually evaluate each news in isolation, fail to capture cross-instance narrative consistency, and thus struggle to address the spread of cluster based fake news driven by social media; (2) Lack of Domain Specific Knowledge for Reasoning: conventional models, which rely solely on knowledge encoded in their parameters during training, struggle to generalize to new or data-scarce domains (e.g., emerging events or niche topics). To tackle these challenges, we introduce Retrieval-Augmented Multimodal Model for Fake News Detection (RAMM). First, RAMM employs a Multimodal Large Language Model (MLLM) as its backbone to capture cross-modal semantic information from news samples. Second, RAMM incorporates an Abstract Narrative Alignment Module. This component adaptively extracts abstract narrative consistency from diverse instances across distinct domains, aggregates relevant knowledge, and thereby enables the modeling of high-level narrative information. Finally, RAMM introduces a Semantic Representation Alignment Module, which aligns the model's decision-making paradigm with that of humans - specifically, it shifts the model's reasoning process from direct inference on multimodal features to an instance-based analogical reasoning process. Extensive experimental results on three public datasets validate the efficacy of our proposed approach. Our code is available at the following link: https://github.com/li-yiheng/RAMM