Problem
Research questions and friction points this paper is trying to address.
fake news video detection
multimodal reasoning
cross-instance semantic correlation
domain-specific knowledge
semantic discrepancy
RASR: Retrieval-Augmented Semantic Reasoning for Fake News Video Detection
🤖 AI Summary
This work addresses the limitations of existing methods in multimodal fake news video detection, which struggle to model global semantic relationships across samples and exhibit limited cross-domain generalization. To overcome these challenges, the authors propose the RASR framework, comprising a Cross-instance Semantic Parsing and Retrieval (CSPR) module, a Domain-Guided Multimodal Reasoning (DGMR) module, and a Multi-View Disentangled Feature Fusion (MVDFF) mechanism. By integrating external evidence, incorporating domain priors, and disentangling multimodal features, RASR enhances both semantic comprehension and cross-domain adaptability. Experimental results demonstrate that RASR significantly outperforms state-of-the-art approaches on the FakeSV and FakeTT datasets, achieving up to a 0.93% improvement in detection accuracy and exhibiting superior robustness and generalization capability.
📝 Abstract
Multimodal fake news video detection is a crucial research direction for maintaining the credibility of online information. Existing studies primarily verify content authenticity by constructing multimodal feature fusion representations or utilizing pre-trained language models to analyze video-text consistency. However, these methods still face the following limitations: (1) lacking cross-instance global semantic correlations, making it difficult to effectively utilize historical associative evidence to verify the current video; (2) semantic discrepancies across domains hinder the transfer of general knowledge, lacking the guidance of domain-specific expert knowledge. To this end, we propose a novel Retrieval-Augmented Semantic Reasoning (RASR) framework. First, a Cross-instance Semantic Parser and Retriever (CSPR) deconstructs the video into high-level semantic primitives and retrieves relevant associative evidence from a dynamic memory bank. Subsequently, a Domain-Guided Multimodal Reasoning (DGMP) module incorporates domain priors to drive an expert multimodal large language model in generating domain-aware, in-depth analysis reports. Finally, a Multi-View Feature Decoupling and Fusion (MVDFF) module integrates multi-dimensional features through an adaptive gating mechanism to achieve robust authenticity determination. Extensive experiments on the FakeSV and FakeTT datasets demonstrate that RASR significantly outperforms state-of-the-art baselines, achieves superior cross-domain generalization, and improves the overall detection accuracy by up to 0.93%.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Retrieval-Augmented Reasoning
Cross-instance Semantic Parsing
Domain-Guided Multimodal Reasoning
Multimodal Fake News Detection
Dynamic Memory Bank
🔎 Similar Papers
No similar papers found.
