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

ACL ARR 2026 January Submission1972 Authors

Keywords: abuse detection, online abuse benchmark, multi-task learning

Abstract: 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 a Target-Aware Multilingual Abuse (TAMA), 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 spans localization. To exploit the hierarchical coupling of these tasks, we propose Cascaded-MTL, a dependency-aware 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://anonymous.4open.science/r/CASCADED-MTL-17FA/README.md

Paper Type: Long

Research Area: Resources and Evaluation

Research Area Keywords: benchmarking, NLP datasets, automatic evaluation of datasets, evaluation methodologies

Contribution Types: NLP engineering experiment, Data resources, Data analysis

Languages Studied: English, Russian, Filipino, Spanish, and Italian

Submission Number: 1972