# Head-wise Modality Specialization within MLLMs for Robust Fake News Detection under Missing Modality

arXiv: https://arxiv.org/abs/2604.09711 · HTML: https://mlsanity.com/paper/2604.09711/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 40 references that are in the map.
- First posted on arXiv 8 Apr 2026.

## Builds on (most cited first, 11 of 11)

- [Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned](https://mlsanity.com/paper/1905.09418/) (2019)
- [Automatic Detection of Fake News](https://mlsanity.com/paper/1708.07104/) (2017)
- [Detecting and Grounding Multi-Modal Media Manipulation](https://mlsanity.com/paper/2304.02556/) (2023)
- [Multimodal Object Detection via Probabilistic Ensembling](https://mlsanity.com/paper/2104.02904/) (2021)
- [Unveiling Visual Perception in Language Models: An Attention Head Analysis Approach](https://mlsanity.com/paper/2412.18108/) (2024)
- [Learning Representations from Imperfect Time Series Data via Tensor Rank Regularization](https://mlsanity.com/paper/1907.01011/) (2019)
- [Learning Missing Modal Electronic Health Records with Unified Multi-modal Data Embedding and Modality-Aware Attention](https://mlsanity.com/paper/2305.02504/) (2023)
- [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)
- [Knowledge Bridger: Towards Training-free Missing Modality Completion](https://mlsanity.com/paper/2502.19834/) (2025)
- [Multimodal Fusion with BERT and Attention Mechanism for Fake News Detection](https://mlsanity.com/paper/2104.11476/) (2021)
- [Fake News Detection and Manipulation Reasoning via Large Vision-Language Models](https://mlsanity.com/paper/2407.02042/) (2024)

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

- [Large Language Models in Misinformation Ecosystems: Misuse, Defense, and Vulnerability](https://mlsanity.com/paper/2607.10402/) (2026)

## Abstract (arXiv)

Multimodal fake news detection (MFND) aims to verify news credibility by jointly exploiting textual and visual evidence. However, real-world news dissemination frequently suffers from missing modality due to deleted images, corrupted screenshots, and similar issues. Thus, robust detection in this scenario requires preserving strong verification ability for each modality, which is challenging in MFND due to insufficient learning of the low-contribution modality and scarce unimodal annotations. To address this issue, we propose Head-wise Modality Specialization within Multimodal Large Language Models (MLLMs) for robust MFND under missing modality. Specifically, we first systematically study attention heads in MLLMs and their relationship with performance under missing modality, showing that modality-critical heads serve as key carriers of unimodal verification ability through their modality specialization. Based on this observation, to better preserve verification ability for the low-contribution modality, we introduce a head-wise specialization mechanism that explicitly allocates these heads to different modalities and preserves their specialization through lower-bound attention constraints. Furthermore, to better exploit scarce unimodal annotations, we propose a Unimodal Knowledge Retention strategy that prevents these heads from drifting away from the unimodal knowledge learned from limited supervision. Experiments show that our method improves robustness under missing modality while preserving performance with full multimodal input.