TAMA: Target-Aware Multilingual Abuse Detection by Cascaded Conditional Multi-Task Learning

Protecting public figures from online abuse requires models that go beyond post-level classification to determine whether abuse is directed at a designated target, characterize the abuse intent, and extract textual evidence. We introduce Target-Aware Multilingual Abuse (TAMA), a benchmark of 9,386 X (Twitter) posts aimed at public figures, with aligned supervision for (i) tri-class target detection, (ii) 12-way fine-grained abuse type classification, and (iii) phrase-level abusive span localization. To exploit the hierarchical coupling of these tasks, we propose Cascaded-MTL, a dependencyaware multi-task framework that conditions downstream predictions on upstream beliefs via three lightweight modules: Cross-Task Feature Fusion (CTF), Task-Adaptive Gating (TAG), and Label-Guided Span Detection (LGSD). Experiments across three multilingual encoders show that Cascaded-MTL consistently yields higher average F1 than single-task and standard multi-task training and delivers robust gains on type classification and span localization. The code and the dataset are released here: https://github. com/zgjiangtoby/CASCADED-MTL. Disclaimer: The examples presented by this paper may be considered offensive or vulgar.