MRAFnd combines retrieval of similar news with multi-agent debate to detect fake news without labeled training data, claiming gains of up to 2.35% accuracy on Weibo-21.
In: Proceedings of the 48th In- ternational ACM SIGIR Conference on Research and Development in Information Retrieval
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.AI 1years
2026 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
MRAFnd: Multimodal Retrieval-Augmented Framework for Zero-Shot Fake News Detection
MRAFnd combines retrieval of similar news with multi-agent debate to detect fake news without labeled training data, claiming gains of up to 2.35% accuracy on Weibo-21.