MANYFAKE benchmark shows state-of-the-art fake news detectors saturate on fully fabricated stories but remain brittle on subtle, optimized falsehoods interwoven with accurate information.
Niagara Falls
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
RASR retrieves cross-video semantic evidence and domain-guided MLLM reports, then fuses multi-view features to beat FakeSV/FakeTT baselines by up to 0.93% accuracy.
citing papers explorer
-
Many Ways to Be Fake: Benchmarking Fake News Detection Under Strategy-Driven AI Generation
MANYFAKE benchmark shows state-of-the-art fake news detectors saturate on fully fabricated stories but remain brittle on subtle, optimized falsehoods interwoven with accurate information.
-
RASR: Retrieval-Augmented Semantic Reasoning for Fake News Video Detection
RASR retrieves cross-video semantic evidence and domain-guided MLLM reports, then fuses multi-view features to beat FakeSV/FakeTT baselines by up to 0.93% accuracy.