# Multilingual Bias Detection and Mitigation for Indian Languages

arXiv: https://arxiv.org/abs/2312.15181 · HTML: https://mlsanity.com/paper/2312.15181/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 23 references that are in the map.
- First posted on arXiv 23 Dec 2023.

## Builds on (most cited first, 13 of 13)

- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [mT5: A massively multilingual pre-trained text-to-text transformer](https://mlsanity.com/paper/2010.11934/) (2020)
- [DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing](https://mlsanity.com/paper/2111.09543/) (2021)
- [InfoXLM: An Information-Theoretic Framework for Cross-Lingual Language Model Pre-Training](https://mlsanity.com/paper/2007.07834/) (2020)
- [Societal Biases in Language Generation: Progress and Challenges](https://mlsanity.com/paper/2105.04054/) (2021)
- [MuRIL: Multilingual Representations for Indian Languages](https://mlsanity.com/paper/2103.10730/) (2021)
- [Samanantar: The Largest Publicly Available Parallel Corpora Collection for 11 Indic Languages](https://mlsanity.com/paper/2104.05596/) (2021)
- [Automatically Neutralizing Subjective Bias in Text](https://mlsanity.com/paper/1911.09709/) (2019)
- [Mitigating Political Bias in Language Models Through Reinforced Calibration](https://mlsanity.com/paper/2104.14795/) (2021)
- [In Plain Sight: Media Bias Through the Lens of Factual Reporting](https://mlsanity.com/paper/1909.02670/) (2019)
- [IndicBART: A Pre-trained Model for Indic Natural Language Generation](https://mlsanity.com/paper/2109.02903/) (2021)
- [Controlled Analyses of Social Biases in Wikipedia Bios](https://mlsanity.com/paper/2101.00078/) (2020)
- [Multilingual Pre-training with Language and Task Adaptation for Multilingual Text Style Transfer](https://mlsanity.com/paper/2203.08552/) (2022)

## Built on by (most cited first, 1 of 1)

- [Multilingual Large Language Model: A Survey of Resources, Taxonomy and Frontiers](https://mlsanity.com/paper/2404.04925/) (2024)

## Abstract (arXiv)

Lack of diverse perspectives causes neutrality bias in Wikipedia content leading to millions of worldwide readers getting exposed by potentially inaccurate information. Hence, neutrality bias detection and mitigation is a critical problem. Although previous studies have proposed effective solutions for English, no work exists for Indian languages. First, we contribute two large datasets, mWikiBias and mWNC, covering 8 languages, for the bias detection and mitigation tasks respectively. Next, we investigate the effectiveness of popular multilingual Transformer-based models for the two tasks by modeling detection as a binary classification problem and mitigation as a style transfer problem. We make the code and data publicly available.