Mitigating Extrinsic Gender Bias for Bangla Classification Tasks

arXiv:2411.10636v2 Announce Type: replace-cross Abstract: In this study, we investigate extrinsic gender bias in Bangla pretrained language models, a largely underexplored area in low-resource languages. To assess this bias, we construct four manually annotated, task-specific benchmark datasets for sentiment analysis, toxicity detection, hate speech detection, and sarcasm detection. Each dataset is augmented using nuanced gender perturbations, where we systematically swap gendered names and terms while preserving semantic content, enabling minimal-pair evaluation of gender-driven prediction shifts. We then propose RandSymKL, a randomized debiasing strategy integrated with symmetric KL divergence and cross-entropy loss to mitigate the bias across task-specific pretrained models. RandSymKL is a refined training approach to integrate these elements in a unified way for extrinsic gender bias mitigation focused on classification tasks. Our approach was evaluated against existing bias mitigation methods, with results showing that our technique not only effectively reduces bias but also maintains competitive accuracy compared to other baseline approaches. To promote further research, we have made both our implementation and datasets publicly available: https://github.com/sajib-kumar/Mitigating-Bangla-Extrinsic-Gender-Bias

Related

• Digital Skin, Digital Bias: Uncovering Tone-Based Biases in LLMs and Emoji Embeddings
• Cross-Lingual Transfer and Parameter-Efficient Adaptation in the Turkic Language Family: A Theoretical Framework for Low-Resource Language Models
• Litmus (Re)Agent: A Benchmark and Agentic System for Predictive Evaluation of Multilingual Models
• Diagnosing and Mitigating Sycophancy and Skepticism in LLM Causal Judgment

Source: arXiv cs.AI | 2026-04-13