A Hybrid Attention Framework for Fake News Detection with Large Language Models

2025-01-21

AI Summary

To address the proliferation of online fake news, this paper proposes an LLM-driven hybrid attention detection framework. Methodologically, it integrates textual statistical features with deep semantic representations from large language models (LLMs) and introduces a novel hybrid attention mechanism that jointly models global semantic consistency and local discriminative cues. Interpretability is enhanced through SHAP-based feature attribution analysis and attention heatmap visualization. The key contribution lies in being the first to organically unify LLM-based semantic understanding, lightweight statistical features, and post-hoc explainability analysis within a single, cohesive architecture. Evaluated on the WELFake dataset, the framework achieves a 1.5% improvement in F1-score over state-of-the-art methods. Moreover, its interpretable outputs—such as salient tokens and feature importance scores—directly support content moderation policy refinement and human-in-the-loop review decisions.

Technology Category

• Natural Language Processing: Fact-Checking / Misinformation Detection (NLP Focus)
• Machine Learning: Large Multimodal Models (LMMs)
• Application Domains: Misinformation & Fake News

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Web Mining and Content Analysis: Large pretrained models with web data
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work

Abstract

With the rapid growth of online information, the spread of fake news has become a serious social challenge. In this study, we propose a novel detection framework based on Large Language Models (LLMs) to identify and classify fake news by integrating textual statistical features and deep semantic features. Our approach utilizes the contextual understanding capability of the large language model for text analysis and introduces a hybrid attention mechanism to focus on feature combinations that are particularly important for fake news identification. Extensive experiments on the WELFake news dataset show that our model significantly outperforms existing methods, with a 1.5% improvement in F1 score. In addition, we assess the interpretability of the model through attention heat maps and SHAP values, providing actionable insights for content review strategies. Our framework provides a scalable and efficient solution to deal with the spread of fake news and helps build a more reliable online information ecosystem.

Problem

• Fake News
• Detection
• Mitigation

Innovation

• High-performance Language Model
• Hybrid Attention Mechanism
• Fake News Detection