LLM-MRD: LLM-Guided Multi-View Reasoning Distillation for Fake News Detection

TL;DR

This paper introduces LLM-MRD, a teacher-student framework that enhances multimodal fake news detection by distilling deep reasoning chains from LLMs into an efficient student model, achieving significant accuracy improvements.

Contribution

The paper proposes a novel multi-view reasoning distillation approach guided by LLMs, addressing limitations of existing methods in comprehensive judgment and computational efficiency.

Findings

Achieves an average of 5.19% accuracy improvement over baselines.

Demonstrates 6.33% higher F1-Fake scores across datasets.

Outperforms state-of-the-art methods in multimodal fake news detection.

Abstract

Multimodal fake news detection is crucial for mitigating societal disinformation. Existing approaches attempt to address this by fusing multimodal features or leveraging Large Language Models (LLMs) for advanced reasoning. However, these methods suffer from serious limitations, including a lack of comprehensive multi-view judgment and fusion, and prohibitive reasoning inefficiency due to the high computational costs of LLMs. To address these issues, we propose \textbf{LLM}-Guided \textbf{M}ulti-View \textbf{R}easoning \textbf{D}istillation for Fake News Detection ( \textbf{LLM-MRD}), a novel teacher-student framework. The Student Multi-view Reasoning module first constructs a comprehensive foundation from textual, visual, and cross-modal perspectives. Then, the Teacher Multi-view Reasoning module generates deep reasoning chains as rich supervision signals. Our core Calibration Distillation mechanism efficiently distills this complex reasoning-derived knowledge into the efficient student model. Experiments show LLM-MRD significantly outperforms state-of-the-art baselines. Notably, it demonstrates a comprehensive average improvement of 5.19\% in ACC and 6.33\% in F1-Fake when evaluated across all competing methods and datasets. Our code is available at https://github.com/Nasuro55/LLM-MRD