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

2026-04-05

AI Summary

This work addresses the limitations of existing fake news detection methods, which often exhibit poor generalization, rely heavily on large amounts of labeled data, and struggle to capture domain-specific characteristics. To overcome these challenges, the authors propose a cross-domain detection framework that integrates a human–large language model (LLM) collaborative annotation mechanism with a domain-aware active learning strategy. The framework leverages LLMs to generate high-quality pseudo-labels and combines domain embedding representation learning with diversity-based sampling to substantially reduce annotation costs while enhancing the model’s capacity to capture cross-domain features. Experimental results demonstrate that the proposed approach significantly outperforms current baselines across multiple benchmark datasets and maintains strong performance even under minimal human supervision.

Abstract

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. To address these issues, we propose CoALFake, a novel approach for cross-domain fake news detection that integrates Human-Large Language Model (LLM) co-annotation with domain-aware Active Learning (AL). Our method employs LLMs for scalable, low-cost annotation while maintaining human oversight to ensure label reliability. By integrating domain embedding techniques, the CoALFake dynamically captures both domain specific nuances and cross-domain patterns, enabling the training of a domain agnostic model. Furthermore, a domain-aware sampling strategy optimizes sample acquisition by prioritizing diverse domain coverage. Experimental results across multiple datasets demonstrate that the proposed approach consistently outperforms various baselines. Our results emphasize that human-LLM co-annotation is a highly cost-effective approach that delivers excellent performance. Evaluations across several datasets show that CoALFake consistently outperforms a range of existing baselines, even with minimal human oversight.

Problem

• fake news detection
• cross-domain
• labelled data scarcity
• domain-specific features
• generalization

Innovation

• Human-LLM co-annotation
• domain-aware active learning
• cross-domain fake news detection
• domain embedding
• collaborative annotation