Causal-GATNet: Explainable Evidence-Aware Fake News Detection by Causal Inference

The proliferation of AI-generated disinformation has amplified the demand for evidence-based fake news detection. Although existing techniques leverage relevant evidence to verify the authenticity of news, they often rely on spurious correlations between superficial patterns and labels instead of genuine evidence-claim reasoning. This tendency degrades the model generalization when applied to real-world scenarios with distribution shifts. To address this challenge, we propose Causal-GATNet1, a unified causal inference architecture that integrates causal intervention with adaptive evidence gating. Our approach: 1) Employs a dual-path causal debiasing framework that compares the standard prediction using all available evidence with a counterfactual prediction generated by blocking bias-inducing evidence, thereby yielding an unbiased output through prediction differencing. 2) Incorporates the Gated Affine Transformation (GAT) mechanism to enhance evidence reliability by combining the source credibility of evidence with their semantics. Experiments on multiple datasets demonstrate that integrating Causal-GATNet with established baseline models such as BERT and MAC significantly improves prediction accuracy and bias mitigation compared to the original implementations.