# Purdah and Patriarchy: Evaluating and Mitigating South Asian Biases in Open-Ended Multilingual LLM Generations

arXiv: https://arxiv.org/abs/2505.18466 · HTML: https://mlsanity.com/paper/2505.18466/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 65 references that are in the map.
- First posted on arXiv 24 May 2025.

## Builds on (most cited first, 14 of 14)

- [mT5: A massively multilingual pre-trained text-to-text transformer](https://mlsanity.com/paper/2010.11934/) (2020)
- [Multilingual Denoising Pre-training for Neural Machine Translation](https://mlsanity.com/paper/2001.08210/) (2020)
- [Beyond English-Centric Multilingual Machine Translation](https://mlsanity.com/paper/2010.11125/) (2020)
- [Self-Diagnosis and Self-Debiasing: A Proposal for Reducing Corpus-Based Bias in NLP](https://mlsanity.com/paper/2103.00453/) (2021)
- [Aya Model: An Instruction Finetuned Open-Access Multilingual Language Model](https://mlsanity.com/paper/2402.07827/) (2024)
- [IndicTrans2: Towards High-Quality and Accessible Machine Translation Models for all 22 Scheduled Indian Languages](https://mlsanity.com/paper/2305.16307/) (2023)
- [Samanantar: The Largest Publicly Available Parallel Corpora Collection for 11 Indic Languages](https://mlsanity.com/paper/2104.05596/) (2021)
- [Self-Debiasing Large Language Models: Zero-Shot Recognition and Reduction of Stereotypes](https://mlsanity.com/paper/2402.01981/) (2024)
- [Re-contextualizing Fairness in NLP: The Case of India](https://mlsanity.com/paper/2209.12226/) (2022)
- [Ethical-Advice Taker: Do Language Models Understand Natural Language Interventions?](https://mlsanity.com/paper/2106.01465/) (2021)
- [IndiBias: A Benchmark Dataset to Measure Social Biases in Language Models for Indian Context](https://mlsanity.com/paper/2403.20147/) (2024)
- [Building Socio-culturally Inclusive Stereotype Resources with Community Engagement](https://mlsanity.com/paper/2307.10514/) (2023)
- [Small Language Model Can Self-correct](https://mlsanity.com/paper/2401.07301/) (2024)
- [Social Bias in Large Language Models For Bangla: An Empirical Study on Gender and Religious Bias](https://mlsanity.com/paper/2407.03536/) (2024)

## Built on by (most cited first, 2 of 2)

- [Camellia: Benchmarking Cultural Biases in LLMs for Asian Languages](https://mlsanity.com/paper/2510.05291/) (2025)
- [Counterfactual Cultural Cues Reduce Medical QA Accuracy in LLMs: Identifier vs Context Effects](https://mlsanity.com/paper/2601.20102/) (2026)

## Abstract (arXiv)

Evaluations of Large Language Models (LLMs) often overlook intersectional and culturally specific biases, particularly in underrepresented multilingual regions like South Asia. This work addresses these gaps by conducting a multilingual and intersectional analysis of LLM outputs across 10 Indo-Aryan and Dravidian languages, identifying how cultural stigmas influenced by purdah and patriarchy are reinforced in generative tasks. We construct a culturally grounded bias lexicon capturing previously unexplored intersectional dimensions including gender, religion, marital status, and number of children. We use our lexicon to quantify intersectional bias and the effectiveness of self-debiasing in open-ended generations (e.g., storytelling, hobbies, and to-do lists), where bias manifests subtly and remains largely unexamined in multilingual contexts. Finally, we evaluate two self-debiasing strategies (simple and complex prompts) to measure their effectiveness in reducing culturally specific bias in Indo-Aryan and Dravidian languages. Our approach offers a nuanced lens into cultural bias by introducing a novel bias lexicon and evaluation framework that extends beyond Eurocentric or small-scale multilingual settings.