TRUST-VL: An Explainable News Assistant for General Multimodal Misinformation Detection

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Yan, Zehong, Qi, Peng, Hsu, Wynne, Lee, Mong Li
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866911240079540224
author Yan, Zehong
Qi, Peng
Hsu, Wynne
Lee, Mong Li
author_facet Yan, Zehong
Qi, Peng
Hsu, Wynne
Lee, Mong Li
contents Multimodal misinformation, encompassing textual, visual, and cross-modal distortions, poses an increasing societal threat that is amplified by generative AI. Existing methods typically focus on a single type of distortion and struggle to generalize to unseen scenarios. In this work, we observe that different distortion types share common reasoning capabilities while also requiring task-specific skills. We hypothesize that joint training across distortion types facilitates knowledge sharing and enhances the model's ability to generalize. To this end, we introduce TRUST-VL, a unified and explainable vision-language model for general multimodal misinformation detection. TRUST-VL incorporates a novel Question-Aware Visual Amplifier module, designed to extract task-specific visual features. To support training, we also construct TRUST-Instruct, a large-scale instruction dataset containing 198K samples featuring structured reasoning chains aligned with human fact-checking workflows. Extensive experiments on both in-domain and zero-shot benchmarks demonstrate that TRUST-VL achieves state-of-the-art performance, while also offering strong generalization and interpretability.
format Preprint
id arxiv_https___arxiv_org_abs_2509_04448
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle TRUST-VL: An Explainable News Assistant for General Multimodal Misinformation Detection
Yan, Zehong
Qi, Peng
Hsu, Wynne
Lee, Mong Li
Computer Vision and Pattern Recognition
Multimedia
Multimodal misinformation, encompassing textual, visual, and cross-modal distortions, poses an increasing societal threat that is amplified by generative AI. Existing methods typically focus on a single type of distortion and struggle to generalize to unseen scenarios. In this work, we observe that different distortion types share common reasoning capabilities while also requiring task-specific skills. We hypothesize that joint training across distortion types facilitates knowledge sharing and enhances the model's ability to generalize. To this end, we introduce TRUST-VL, a unified and explainable vision-language model for general multimodal misinformation detection. TRUST-VL incorporates a novel Question-Aware Visual Amplifier module, designed to extract task-specific visual features. To support training, we also construct TRUST-Instruct, a large-scale instruction dataset containing 198K samples featuring structured reasoning chains aligned with human fact-checking workflows. Extensive experiments on both in-domain and zero-shot benchmarks demonstrate that TRUST-VL achieves state-of-the-art performance, while also offering strong generalization and interpretability.
title TRUST-VL: An Explainable News Assistant for General Multimodal Misinformation Detection
topic Computer Vision and Pattern Recognition
Multimedia
url https://arxiv.org/abs/2509.04448