BanHADEX: Towards Explainable HAte Speech Detection in Bangla Using Human Annotated EXplanation
Faisal Hossain Raquib Rajshahi University of Engineering and Technology, Akm Moshiur Rahman Mazumder Independent University, Bangladesh, Md Fahim Penta Global Limited and Independent University, Bangladesh, Md Tahmid Hasan Fuad University of Manitoba, Md Farhan Ishmam, Faria Sultana, M Ashraful Amin Independent University, Bangladesh, Amin Ahsan Ali 等 9 位作者
原文摘要
Online safety in low-resource languages hinges not only on accurate hate speech detection but also on transparent, culturally grounded explanations. Yet prior works in Bangla largely focus on hate classification, while overlooking interpretability. We address this gap by introducing BanHADEX, the first hate explainability dataset in Bangla with human-annotated labels. BanHADEX contains 19,203 YouTube comments spanning April 2024–June 2025, annotated for binary hate classification with seven fine-grained hate categories, seven target groups, and concise explanations for each sample. Our data pipeline relies on a two-stage annotation protocol that uses majority voting for robust labeling. Our rich suite of experiments on open and closed-source LLMs reveals that explanation-guided LoRA substantially outperforms both classification and explanation quality across prompting and fine-tuning strategies. BanHADEX establishes the groundworks for faithful interpretability and safer moderation in linguistically rich yet under-resourced languages.
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表