Investigating Bias in Multilingual Language Models: Cross-Lingual Transfer of Debiasing Techniques

Manon Reusens, Philipp Borchert, Margot Mieskes, Jochen De Weerdt, Bart Baesens

Submission Type: Regular Short Paper

Submission Track: Multilinguality and Linguistic Diversity

Submission Track 2: Ethics in NLP

Keywords: bias mitigation, cross-lingual transferability, multilingual BERT

TL;DR: This paper shows that cross-lingual transfer of debiasing is possible and yields promising results.

Abstract: 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.

Submission Number: 2927