CoALFake: Collaborative Active Learning with Human-LLM Co-Annotation for Cross-Domain Fake News Detection

ArXi:2604.04174v1 Announce Type: new The proliferation of fake news across diverse domains highlights critical limitations in current detection systems, which often exhibit narrow domain specificity and poor generalization. Existing cross-domain approaches face two key challenges: (1) reliance on labelled data, which is frequently unavailable and resource intensive to acquire and (2) information loss caused by rigid domain categorization or neglect of domain-specific features.