# TriSPrompt: A Hierarchical Soft Prompt Model for Multimodal Rumor Detection with Incomplete Modalities

arXiv: https://arxiv.org/abs/2509.19352 · HTML: https://mlsanity.com/paper/2509.19352/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 36 references that are in the map.
- First posted on arXiv 18 Sep 2025.

## Builds on (most cited first, 10 of 10)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks](https://mlsanity.com/paper/1908.02265/) (2019)
- [MDFEND: Multi-domain Fake News Detection](https://mlsanity.com/paper/2201.00987/) (2022)
- [Exploiting Multi-domain Visual Information for Fake News Detection](https://mlsanity.com/paper/1908.04472/) (2019)
- [Improving Fake News Detection by Using an Entity-enhanced Framework to Fuse Diverse Multimodal Clues](https://mlsanity.com/paper/2108.10509/) (2021)
- [CED: Credible Early Detection of Social Media Rumors](https://mlsanity.com/paper/1811.04175/) (2018)
- [Call Attention to Rumors: Deep Attention Based Recurrent Neural Networks for Early Rumor Detection](https://mlsanity.com/paper/1704.05973/) (2017)
- [RedCore: Relative Advantage Aware Cross-modal Representation Learning for Missing Modalities with Imbalanced Missing Rates](https://mlsanity.com/paper/2312.10386/) (2023)

## Built on by (most cited first, 2 of 2)

- [The Facade of Truth: Uncovering and Mitigating LLM Susceptibility to Deceptive Evidence](https://mlsanity.com/paper/2601.05478/) (2026)
- [Optimizing Soft Prompt Tuning via Structural Evolution](https://mlsanity.com/paper/2602.16500/) (2026)

## Abstract (arXiv)

The widespread presence of incomplete modalities in multimodal data poses a significant challenge to achieving accurate rumor detection. Existing multimodal rumor detection methods primarily focus on learning joint modality representations from complete multimodal training data, rendering them ineffective in addressing the common occurrence of missing modalities in real-world scenarios. In this paper, we propose a hierarchical soft prompt model textsfTriSPrompt, which integrates three types of prompts, textiti.e., modality-aware (MA) prompt, modality-missing (MM) prompt, and mutual-views (MV) prompt, to effectively detect rumors in incomplete multimodal data. The MA prompt captures both heterogeneous information from specific modalities and homogeneous features from available data, aiding in modality recovery. The MM prompt models missing states in incomplete data, enhancing the model's adaptability to missing information. The MV prompt learns relationships between subjective (textiti.e., text and image) and objective (textiti.e., comments) perspectives, effectively detecting rumors. Extensive experiments on three real-world benchmarks demonstrate that textsfTriSPrompt achieves an accuracy gain of over 13% compared to state-of-the-art methods. The codes and datasets are available at https: //anonymous.4open.science/r/code-3E88.