通过上下文建模提升新闻偏见检测准确率，效果优于现有方法。
HierBias: Context-Conditioned Hierarchical Media Bias Detection with Multi-Task Type Classification
- 分层结构融合句子间上下文信息，更贴近人类判断方式。
- 在BABE和BASIL数据集上分别达0.853 F1和0.723 MCC，显著领先。
- 适合需要高精度偏见识别的媒体分析与内容审核场景。
媒体偏见检测对保障信息公平传播至关重要，但现有句级方法独立分类每句话，忽略人类标注者自然使用的句间上下文信号。我们提出HierBias，一种基于上下文的层次化偏见检测模型，正式建模文档级上下文以支持偏见预测。引入上下文条件偏见概率，并理论证明：当句间存在互信息时，利用上下文可严格降低贝叶斯误差。多任务泛化界进一步表明，联合训练二分类偏见检测与四类细粒度偏见类型分类，能提升小规模标注语料下的样本效率。架构上，HierBias结合句子级RoBERTa编码器、跨句Transformer聚合模块及双输出头，分别实现二分类与四类类型分类。在BABE和BASIL数据集上，分别取得0.853 F1和0.723 MCC，较当前最优模型提升2.6% F1与4.3% MCC（McNemar检验，p < 0.05）。消融实验验证各理论组件均独立且持续贡献。
原文摘要 · Abstract (English)
Media bias detection is a critical task for ensuring fair and balanced information dissemination, yet existing sentence-level approaches classify each sentence independently, ignoring inter-sentence contextual signals that human annotators naturally exploit. We present \textbf{HierBias}, a hierarchical context-conditioned media bias detector that formally models document context in bias prediction. We introduce the \emph{context-conditioned bias probability} and prove theoretically that leveraging document context strictly reduces the Bayes error of sentence-level classification when inter-sentence mutual information is non-zero. A multi-task generalization bound further establishes that jointly training binary bias detection and fine-grained bias type classification improves sample efficiency on small annotated corpora. Architecturally, HierBias pairs a sentence-level RoBERTa encoder with a cross-sentence Transformer aggregator and dual output heads for binary detection and four-class type classification. Evaluated on BABE and BASIL, HierBias achieves 0.853 F1 and 0.723 MCC, surpassing the state-of-the-art bias-detector by $+2.6\%$ F1 and $+4.3\%$ MCC (McNemar's test, $p < 0.05$). Ablation experiments confirm that each theoretical component contributes independently and consistently.
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。