Nip Rumors in the Bud: Retrieval-Guided Topic-Level Adaptation for Test-Time Fake News Video Detection

2026-01-17

AI Summary

This work addresses the challenge of detecting fake news videos involving emerging events or unseen topics when the distribution of news themes differs between training and testing. To this end, the authors propose RADAR, a novel retrieval-guided test-time adaptation framework that enables online detection of out-of-distribution fake news without access to source-domain data. RADAR integrates three core mechanisms: entropy-based selective retrieval, stable anchor–guided cross-domain alignment, and target-domain-aware self-training. These components collectively facilitate effective adaptation to novel topics during inference. Extensive experiments demonstrate that RADAR significantly outperforms existing methods across multiple benchmarks, exhibiting superior dynamic adaptability and detection performance under distribution shifts.

Technology Category

• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning
• Computer Vision: Adversarial Attacks & Robustness
• Natural Language Processing: Fact-Checking / Misinformation Detection (NLP Focus)

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Web Mining and Content Analysis: Topic discovery and tracking

Abstract

Fake News Video Detection (FNVD) is critical for social stability. Existing methods typically assume consistent news topic distribution between training and test phases, failing to detect fake news videos tied to emerging events and unseen topics. To bridge this gap, we introduce RADAR, the first framework that enables test-time adaptation to unseen news videos. RADAR pioneers a new retrieval-guided adaptation paradigm that leverages stable (source-close) videos from the target domain to guide robust adaptation of semantically related but unstable instances. Specifically, we propose an Entropy Selection-Based Retrieval mechanism that provides videos with stable (low-entropy), relevant references for adaptation. We also introduce a Stable Anchor-Guided Alignment module that explicitly aligns unstable instances'representations to the source domain via distribution-level matching with their stable references, mitigating severe domain discrepancies. Finally, our novel Target-Domain Aware Self-Training paradigm can generate informative pseudo-labels augmented by stable references, capturing varying and imbalanced category distributions in the target domain and enabling RADAR to adapt to the fast-changing label distributions. Extensive experiments demonstrate that RADAR achieves superior performance for test-time FNVD, enabling strong on-the-fly adaptation to unseen fake news video topics.

Problem

• Fake News Video Detection
• Test-Time Adaptation
• Unseen Topics
• Domain Shift
• Emerging Events

Innovation

• test-time adaptation
• retrieval-guided learning
• fake news video detection
• domain alignment
• self-training