This paper investigates the transferability of debiasing techniques across different languages within multilingual models. We examine the applicability of these techniques in English, French, German, and Dutch. Using multilingual BERT (mBERT), we demonstrate that cross-lingual transfer of debiasing techniques is not only feasible but also yields promising results. Surprisingly, our findings reveal no performance disadvantages when applying these techniques to non-English languages. Using translations of the CrowS-Pairs dataset, our analysis identifies SentenceDebias as the best technique across different languages, reducing bias in mBERT by an average of 13%. We also find that debiasing techniques with additional pretraining exhibit enhanced cross-lingual effectiveness for the languages included in the analyses, particularly in lower-resource languages. These novel insights contribute to a deeper understanding of bias mitigation in multilingual language models and provide practical guidance for debiasing techniques in different language contexts.

翻译：本文研究了多语言模型中不同语言间去偏技术的可迁移性。我们考察了这些技术在英语、法语、德语和荷兰语中的适用性。通过使用多语言BERT模型（mBERT），我们证明去偏技术的跨语言迁移不仅可行，而且能取得显著效果。令人意外的是，我们的发现表明将这些技术应用于非英语语言时，并没有造成性能损失。基于CrowS-Pairs数据集的翻译版本，我们的分析识别出SentenceDebias是跨语言表现最佳的技术，可使mBERT的偏差平均降低13%。我们还发现，包含额外预训练阶段的去偏技术在分析涉及的语言中展现出更强的跨语言效果，尤其在低资源语言中表现更为突出。这些新发现不仅加深了对多语言语言模型中偏差缓解机制的理解，还为不同语言环境下的去偏技术提供了实践指导。