RASR: Retrieval-Augmented Semantic Reasoning for Fake News Video Detection

TL;DR

The paper introduces RASR, a novel framework for fake news video detection that leverages retrieval-augmented semantic reasoning, domain priors, and multi-view feature fusion to improve accuracy and cross-domain generalization.

Contribution

It proposes a retrieval-augmented semantic reasoning framework with a semantic parser, domain-guided reasoning, and feature fusion modules, advancing fake news video detection methods.

Findings

RASR outperforms state-of-the-art baselines on FakeSV and FakeTT datasets.

Achieves up to 0.93% improvement in detection accuracy.

Demonstrates superior cross-domain generalization capabilities.

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%.