用大模型+混合注意力机制提升假新闻识别准确率
A Hybrid Attention Framework for Fake News Detection with Large Language Models
- 融合文本统计与语义特征，通过混合注意力聚焦关键信息
- 在WELFake数据集上F1得分提升1.5%，优于现有方法
- 支持可解释性分析，适合内容审核与平台风控场景
随着在线信息的快速增长，虚假新闻的传播已成为严重的社会挑战。本文提出一种基于大语言模型（LLMs）的新型检测框架，通过整合文本统计特征与深层语义特征来识别和分类虚假新闻。该方法利用大语言模型的上下文理解能力进行文本分析，并引入混合注意力机制，聚焦于对虚假新闻识别尤为重要的特征组合。在WELFake新闻数据集上的大量实验表明，该模型显著优于现有方法，F1分数提升1.5%。此外，我们通过注意力热力图和SHAP值评估了模型的可解释性，为内容审查策略提供了可操作的洞察。该框架为应对虚假新闻传播提供了可扩展、高效的解决方案，有助于构建更可靠的网络信息生态。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。