# Mitigating Extrinsic Gender Bias for Bangla Classification Tasks

arXiv: https://arxiv.org/abs/2411.10636 · HTML: https://mlsanity.com/paper/2411.10636/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 27 of its 61 references that are in the map.
- First posted on arXiv 16 Nov 2024.

## Builds on (most cited first, 27 of 27)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings](https://mlsanity.com/paper/1607.06520/) (2016)
- [Language (Technology) is Power: A Critical Survey of "Bias" in NLP](https://mlsanity.com/paper/2005.14050/) (2020)
- [Semantics derived automatically from language corpora contain human-like biases](https://mlsanity.com/paper/1608.07187/) (2016)
- [Gender Bias in Coreference Resolution](https://mlsanity.com/paper/1804.09301/) (2018)
- [Mitigating Gender Bias in Natural Language Processing: Literature Review](https://mlsanity.com/paper/1906.08976/) (2019)
- [Examining Gender and Race Bias in Two Hundred Sentiment Analysis Systems](https://mlsanity.com/paper/1805.04508/) (2018)
- [Measuring and Reducing Gendered Correlations in Pre-trained Models](https://mlsanity.com/paper/2010.06032/) (2020)
- [MuRIL: Multilingual Representations for Indian Languages](https://mlsanity.com/paper/2103.10730/) (2021)
- [Bias Mitigation for Machine Learning Classifiers: A Comprehensive Survey](https://mlsanity.com/paper/2207.07068/) (2022)
- [Hate Speech detection in the Bengali language: A dataset and its baseline evaluation](https://mlsanity.com/paper/2012.09686/) (2020)
- [Data Bootstrapping Approaches to Improve Low Resource Abusive Language Detection for Indic Languages](https://mlsanity.com/paper/2204.12543/) (2022)
- [BenLLMEval: A Comprehensive Evaluation into the Potentials and Pitfalls of Large Language Models on Bengali NLP](https://mlsanity.com/paper/2309.13173/) (2023)
- [Optimising Equal Opportunity Fairness in Model Training](https://mlsanity.com/paper/2205.02393/) (2022)
- [Gender Bias in BERT -- Measuring and Analysing Biases through Sentiment Rating in a Realistic Downstream Classification Task](https://mlsanity.com/paper/2306.15298/) (2023)
- [Social Bias in Large Language Models For Bangla: An Empirical Study on Gender and Religious Bias](https://mlsanity.com/paper/2407.03536/) (2024)
- [How Far Can It Go?: On Intrinsic Gender Bias Mitigation for Text Classification](https://mlsanity.com/paper/2301.12855/) (2023)
- [Effective Controllable Bias Mitigation for Classification and Retrieval using Gate Adapters](https://mlsanity.com/paper/2401.16457/) (2024)
- [BLP-2023 Task 2: Sentiment Analysis](https://mlsanity.com/paper/2310.16183/) (2023)
- [Counter-GAP: Counterfactual Bias Evaluation through Gendered Ambiguous Pronouns](https://mlsanity.com/paper/2302.05674/) (2023)
- [Addressing Both Statistical and Causal Gender Fairness in NLP Models](https://mlsanity.com/paper/2404.00463/) (2024)
- [An Empirical Study on the Characteristics of Bias upon Context Length Variation for Bangla](https://mlsanity.com/paper/2406.17375/) (2024)
- [BanglaSarc: A Dataset for Sarcasm Detection](https://mlsanity.com/paper/2209.13461/) (2022)
- [Improving Bias in Facial Attribute Classification: A Combined Impact of KL Divergence induced Loss Function and Dual Attention](https://mlsanity.com/paper/2410.11176/) (2024)

## Abstract (arXiv)

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