When Does Hate Transfer? A Large-Scale Study of Cross-Lingual Hate Speech Detection

ACL ARR 2026 January Submission6111 Authors

Keywords: Hate Speech Detection, Transfer Learning, Low Resource Language, Large Language Models (LLMs), Multilingual NLP

Abstract: Effective detection of hate content is essential for maintaining healthy online communities, yet performance can vary substantially across languages. This work investigates a core practical question: Can training data from one language support hate-speech detection in another language with comparable performance? To answer this question, we conduct a large-scale study across 14 languages. Our analysis shows that transfer effectiveness could depend on several factors—including, but not limited to, dataset size, resources and temporal overlap. At the same time, we observe consistent patterns in which certain language pairs exhibit stronger transfer performance. Upon further analysis, we find that these patterns can be attributed to cultural cues or shared societal characteristics. Our analysis includes low-resource languages, offering practical insights into when cross-lingual transfer can support them and where its limitations emerge. These findings provide guidance for designing more reliable and generalizable hate detection systems.

Paper Type: Long

Research Area: Computational Social Science, Cultural Analytics, and NLP for Social Good

Research Area Keywords: Hate Speech Detection, Transfer Learning, Low Resource Language, Large Language Models (LLMs), Multilingual NLP

Contribution Types: Approaches to low-resource settings

Languages Studied: English, German, French, Spanish, Chinese, Korean, Malay, Indonesian, Persian, Arabic, Urdu, Hindi, Bengali, Turkish

Submission Number: 6111