TRUST-VL: An Explainable News Assistant for General Multimodal Misinformation Detection
This addresses the societal threat of multimodal misinformation amplified by generative AI, offering a generalizable and explainable solution, though it appears incremental as it builds on existing vision-language models.
The paper tackles the problem of multimodal misinformation detection by proposing TRUST-VL, a unified vision-language model that achieves state-of-the-art performance on in-domain and zero-shot benchmarks, with results supported by extensive experiments.
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.