Go to ACL ARR 2025 February homepageFrom Measurement to Mitigation: Exploring the Transferability of Debiasing Approaches to Gender Bias in Maltese Language Models
Abstract: The advancement of Large Language Models (LLMs) has transformed Natural Language Processing (NLP), enabling performance across diverse tasks with little task-specific training. However, LLMs remain susceptible to social biases, particularly reflecting harmful stereotypes from training data, which can disproportionately affect marginalized communities.
While bias evaluation and mitigation efforts have progressed for English-centric models, research on low-resourced and morphologically rich languages remains limited. This research investigates the transferability of debiasing methods to Maltese language models, focusing on BERTu and mBERTu, BERT-based monolingual and multilingual models respectively. Bias measurement and mitigation techniques from English are adapted to Maltese, using benchmarks like CrowS-Pairs and SEAT, alongside debiasing methods Counterfactual Data Augmentation, Dropout Regularization, Auto-Debias, and GuiDebias. We also contribute by creating important evaluation datasets in Maltese, creating new resources for future work.
The findings highlight the challenges of applying existing bias mitigation methods to linguistically complex languages, underscoring the need for more inclusive approaches in multilingual NLP development.
Paper Type: Long
Research Area: Ethics, Bias, and Fairness
Research Area Keywords: model bias/fairness evaluation, model bias/unfairness mitigation, less-resourced languages
Contribution Types: Model analysis & interpretability, NLP engineering experiment, Theory
Languages Studied: Maltese
Submission Number: 8456
Loading