As large language models (LLMs) become increasingly prevalent in global applications, ensuring that they are toxicity-free across diverse linguistic contexts remains a critical challenge. We explore "Cross-lingual Detoxification", a cross-lingual paradigm that mitigates toxicity, enabling detoxification capabilities to transfer between high and low-resource languages across different script families. We analyze cross-lingual detoxification's effectiveness through 392 extensive settings to evaluate toxicity reduction in cross-distribution settings with limited data and investigate how mitigation impacts model performance on non-toxic tasks, revealing trade-offs between safety and knowledge preservation. Our code and dataset are publicly available at https://github.com/himanshubeniwal/Breaking-mBad.
@article{arxiv.2505.16722,
title = {Breaking mBad! Supervised Fine-tuning for Cross-Lingual Detoxification},
author = {Himanshu Beniwal and Youngwoo Kim and Maarten Sap and Soham Dan and Thomas Hartvigsen},
journal= {arXiv preprint arXiv:2505.16722},
year = {2025}
}