Search papers, labs, and topics across Lattice.
The paper introduces RASR, a Retrieval-Augmented Semantic Reasoning framework for fake news video detection that addresses limitations in existing methods by incorporating cross-instance global semantic correlations and domain-specific expert knowledge. RASR uses a Cross-instance Semantic Parser and Retriever (CSPR) to retrieve relevant associative evidence and a Domain-Guided Multimodal Reasoning (DGMP) module to generate domain-aware analysis reports using a multimodal LLM. Experiments on FakeSV and FakeTT datasets show RASR outperforms state-of-the-art baselines, improving detection accuracy by up to 0.93%.
Fake news detection gets a boost: RASR leverages retrieval-augmented semantic reasoning and domain-guided multimodal reasoning to significantly outperform existing methods, achieving up to 0.93% accuracy improvement.
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%.
