提出细粒度解释方法，让谣言检测模型的决策更透明可信。
Contrastive Token-level Explanations for Graph-based Rumour Detection
- 基于对比思想的逐层归因法，精准定位文本中关键信息词
- 在三个公开数据集上验证，解释结果与真实谣言高度一致
- 适合关注AI决策可解释性的研究人员和安全团队
社交媒体的普及加速了信息传播，但也助长了有害谣言的扩散，可能扰乱经济、影响政治、加剧公共卫生危机，如新冠疫情。尽管图神经网络（GNN）在自动化谣言检测方面展现出显著潜力，但其预测过程缺乏透明性，难以解释。现有图可解释性方法难以应对高维文本嵌入中特征维度间的依赖关系。本文提出对比式分层归因法（CT-LRP），一种新型框架，旨在提升基于GNN的谣言检测可解释性。该方法提供细粒度的词级别解释，增强解释的精确性和可读性。我们在三个公开的谣言检测数据集上对多种GNN模型进行评估，结果表明CT-LRP能持续生成高保真、有意义的解释，为构建更稳健、可信的谣言检测系统奠定基础。
原文摘要 · Abstract (English)
The widespread use of social media has accelerated the dissemination of information, but it has also facilitated the spread of harmful rumours, which can disrupt economies, influence political outcomes, and exacerbate public health crises, such as the COVID-19 pandemic. While Graph Neural Network (GNN)-based approaches have shown significant promise in automated rumour detection, they often lack transparency, making their predictions difficult to interpret. Existing graph explainability techniques fall short in addressing the unique challenges posed by the dependencies among feature dimensions in high-dimensional text embeddings used in GNN-based models. In this paper, we introduce Contrastive Token Layerwise Relevance Propagation (CT-LRP), a novel framework designed to enhance the explainability of GNN-based rumour detection. CT-LRP extends current graph explainability methods by providing token-level explanations that offer greater granularity and interpretability. We evaluate the effectiveness of CT-LRP across multiple GNN models trained on three publicly available rumour detection datasets, demonstrating that it consistently produces high-fidelity, meaningful explanations, paving the way for more robust and trustworthy rumour detection systems.
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。