多语言宣传检测数据集，支持技术分类与定位解释。
ProBel: Propaganda Detection with Techniques, Spans, and Explanations
- 构建双语（阿拉伯/英语）宣传检测数据集，覆盖23种技巧和6类粗粒度分类。
- 联合训练模型在跨语言、跨任务上表现最优，零样本提示也有效。
- 强调标注层次影响迁移效果，适合做多任务多语言传播分析的研究者。
宣传检测包含从句子级判断到技巧分类和片段识别等多个预测层级。然而，阿拉伯语和英语中这些层级的监督信号如何协同仍不明确。我们提出ProBel，一个阿拉伯语和英语资源，对同一新闻句子进行二值标签、23种宣传技巧的多标签标注（分为6个粗粒度类别）、技巧标注片段及参考解释的对齐。该数据集包含更大规模的英文语料，并支持两种语言下的匹配二值、粗粒度、多标签和片段级任务。我们在统一设置下评估了零样本提示、任务特定微调和联合训练。单一双语多任务模型整体表现最佳，且在不同任务和语言间保持竞争力。跨任务分析表明，迁移能力依赖于监督层级：联合分类训练能保持二值预测性能，而仅片段训练会削弱句子级预测。联合双语训练结果最稳定，而单语微调可能降低向另一语言的迁移能力。数据、代码和评估脚本将公开发布。
原文摘要 · Abstract (English)
Propaganda detection includes several related prediction levels, ranging from sentence-level decisions to technique classification and span identification. However, it remains unclear how supervision at these levels interacts when learned jointly across Arabic and English. We present ProBel, an Arabic and English resource that aligns binary labels, multi-label annotations over 23 propaganda techniques grouped into six coarse categories, technique-labeled spans, and reference explanations for the same news sentences. It includes a substantially larger English collection and supports matched binary, coarse-grained, multi-label, and span-level tasks in both languages. We evaluate zero-shot prompting, task-specific fine-tuning, and joint training under a shared setup. A single bilingual multi-task model achieves the best overall performance and remains competitive across tasks and languages. Cross-task analysis shows that transfer depends on the supervision level. Joint classification training preserves binary performance, whereas span-only training can weaken sentence-level prediction. Joint bilingual training yields the most stable results, while monolingual fine-tuning can reduce transfer to the other language. We will release the data, code, and evaluation scripts.
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。