Elamur Research⌕
☰
home / papers / 2026 / Purdah and Patriarchy: Evaluating and Mitigating South Asian Biases in Open-Ended Multilingual LLM Generations

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

Paper · 2026 · Mamnuya Rinki, Chahat Raj, Anjishnu Mukherjee et al.

Summary

The paper examines a gap in LLM bias research: culturally specific, intersectional stereotypes in South Asia that are tied to purdah and patriarchy. Examples include stigma around childlessness, marital status and women's autonomy. Prior work has mostly covered English, a few high-resource languages, caste bias, or constrained QA formats. The authors built a balanced dataset of open-ended generations from mT0-xxl in 10 Indo-Aryan and Dravidian languages. Prompts combined four identity dimensions (religion, gender, marital status, number of children) with three everyday tasks. Outputs were translated into English with IndicTrans2. They were then scored with Bias TF-IDF using a new South Asian bias lexicon drawn from sociological literature. The authors also tested two post-hoc self-debiasing prompts, one generic and one identity-specific, both in an "If-or-Else" style meant to prevent over-correction. Bias was higher in Indo-Aryan languages and in task-oriented outputs, especially to-do lists. Debiasing helped only slightly, and only for Dravidian languages. The work offers a reusable, non-Eurocentric resource for auditing multilingual LLMs.

Key points

  • Dataset size: 100,800 entries across 48 identity combinations.
  • Languages: 6 Indo-Aryan (Bengali, Hindi, Urdu, Punjabi, Marathi, Gujarati) and 4 Dravidian (Telugu, Kannada, Malayalam, Tamil).
  • Tasks: daily to-do lists, hobbies/values descriptions, and storytelling set at home, school, work or hospital.
  • Pipeline:
    • mT0-xxl generates the outputs, and IndicTrans2 translates them into English.
    • Translations were spot-checked on 10–20 samples per language.
    • The lexicon was expanded with NLTK and spaCy synonym generation.
  • Findings:
    • Indo-Aryan languages, linked to regions where purdah is practised, show higher bias.
    • To-do lists are the most biased task.
    • A complex, highly specific debiasing prompt gives marginal reductions in Dravidian languages and no notable gain in Indo-Aryan ones.
  • Release and limitations:
    • Data, code and the lexicon are released at github.com/mamnuya/purdah_and_patriarchy.
    • The authors acknowledge that the lexicon is non-exhaustive.
    • They also note that TF-IDF scoring is blind to context.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

 Fields, topics and concepts

📚 Shelves 6The field of science this work belongs to (OpenAlex fields).Computer Science · 16,667 worksArtificial Intelligence · 16,194 worksArts and Humanities · 16,039 worksLanguage and Linguistics · 15,891 worksSocial Sciences · 1,772 worksSafety Research · 543 works

🧭 Topics 2Research subjects and languages the work is about.Language models & pretraining · 3,320 worksMultilingual & cross-lingual NLP · 828 works

Cite

Cite as Mamnuya Rinki, Chahat Raj, Anjishnu Mukherjee and Ziwei Zhu. 2026. Purdah and Patriarchy: Evaluating and Mitigating South Asian Biases in Open-Ended Multilingual LLM Generations. Proceedings of the 6th Workshop on Trustworthy NLP (TrustNLP 2026).

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2026.trustnlp-main.18

@inproceedings{rinki2026purdah,
  title = {{Purdah and Patriarchy: Evaluating and Mitigating South Asian Biases in Open-Ended Multilingual LLM Generations}},
  author = {Mamnuya Rinki, Chahat Raj, Anjishnu Mukherjee and Ziwei Zhu},
  booktitle = {Proceedings of the 6th Workshop on Trustworthy NLP (TrustNLP 2026)},
  year = {2026},
  doi = {10.18653/v1/2026.trustnlp-main.18},
  url = {https://doi.org/10.18653/v1/2026.trustnlp-main.18}
}

References

64 references, 7 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Prima Alam, Leesa Lin, Nandan Thakkar, Abhi Thaker, and Cicely Marston. 2024. Socio-sexual norms and young people’s sexual health in urban bangladesh, india, nepal and pakistan: A qualitative scoping review. PLOS global public health, 4:e0002179–e0002179. find
  2. Sumera Ali, Raafay Sophie, Ayesha M Imam, Faisal I Khan, Syed F Ali, Annum Shaikh, and Syed Farid-ul Hasnain. 2011. Knowledge, perceptions and myths regarding infertility among selected adult population in pakistan: a cross-sectional study. BMC Public Health, 11. find
  3. Sumera Arshad, Muhammad Zahid Naeem, Muhammad Azmat Hayat, Ramona Birau, Peter Fernandes Wanke, Yong Tan, Lucia Paliu-Popa, and Iuliana Carmen Bărbăcioru. 2024. Examining divorce risk through gender roles in pakistan. Womens Studies International Forum, 104:102918–102918. find
  4. Greta Bauer. 2025. Intersectionality, Sex/Gender Entanglement, and Research Design, pages 139–151. Springer Nature Switzerland, Cham. find
  5. Shaily Bhatt, Sunipa Dev, Partha Talukdar, Shachi Dave, and Vinodkumar Prabhakaran. 2022. Re-contextualizing fairness in NLP: The case of India. In Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conferen… find
  6. Steven Bird, Ewan Klein, and Edward Loper. 2009. Natural language processing with Python: analyzing text with the natural language toolkit. “O’Reilly Media, Inc.". find
  7. J Burr. 2002. Cultural stereotypes of women from south asian communities: mental health care professionals’ explanations for patterns of suicide and depression. Social Science & Medicine, 55:835–845. find
  8. Javier Cerrato and Eva Cifre. 2018. Gender inequality in household chores and work-family conflict. Frontiers in Psychology, 9. find
  9. Fiona Cross-Sudworth. 2006. Infertility issues for south asian women. Diversity and equality in health and care, 3:281–287. find
  10. Raj Dabre and Anoop Kunchukuttan. 2024. Findings of WMT 2024’s MultiIndic22MT shared task for machine translation of 22 Indian languages. In Proceedings of the Ninth Conference on Machine Translation, pages 669–676, Miami, Florida, USA. Association for Computational Linguistics. find
  11. Dipto Das, Shion Guha, and Bryan Semaan. 2023. Toward cultural bias evaluation datasets: The case of bengali gender, religious, and national identity. Association for Computational Linguistics. find
  12. Sunipa Dev, Jaya Goyal, Dinesh Tewari, Shachi Dave, and Vinodkumar Prabhakaran. 2023. Building socio-culturally inclusive stereotype resources with community engagement. In Proceedings of the 37th International Conference on Neural Information Processing Systems, NIPS ’23, Red Hook, NY, USA. Curran… find
  13. Hannah Devinney, Jenny Björklund, and Henrik Björklund. 2024. We don’t talk about that: Case studies on intersectional analysis of social bias in large language models. Proceedings of the 5th Workshop on Gender Bias in Natural Language Processing (GeBNLP), pages 33–44. find
  14. Leela Dube. 1996. Kinship and gender in south and southeast asia: patterns and contrasts. find
  15. Caroline A. Erentzen, Veronica N. Z. Bergstrom, Norman Zeng, and Alison L. Chasteen. 2023. The gendered nature of muslim and christian stereotypes in the united states. Group Processes & Intergroup Relations, 26(8):1726–1749. find
  16. Angela Fan, Shruti Bhosale, Holger Schwenk, Zhiyi Ma, Ahmed El-Kishky, Siddharth Goyal, Mandeep Baines, Onur Celebi, Guillaume Wenzek, Vishrav Chaudhary, Naman Goyal, Tom Birch, Vitaliy Liptchinsky, Sergey Edunov, Edouard Grave, Michael Auli, and Armand Joulin. 2020. Beyond english-centric multiling… find
  17. Xiao Fang, Shangkun Che, Minjia Mao, Hongzhe Zhang, Ming Zhao, and Xiaohang Zhao. 2024. Bias of ai-generated content: an examination of news produced by large language models. Scientific Reports, 14:5224. find
  18. Fariyal F Fikree and Omrana Pasha. 2004. Role of gender in health disparity: the south asian context. BMJ, 328:823–826. find
  19. Jay Gala, Pranjal A. Chitale, Raghavan AK, Varun Gumma, Sumanth Doddapaneni, Aswanth Kumar, Janki Nawale, Anupama Sujatha, Ratish Puduppully, Vivek Raghavan, Pratyush Kumar, Mitesh M. Khapra, Raj Dabre, and Anoop Kunchukuttan. 2023. Indictrans2: Towards high-quality and accessible machine translatio…
  20. Isabel O. Gallegos, Ryan Aponte, Ryan A. Rossi, Joe Barrow, Mehrab Tanjim, Tong Yu, Hanieh Deilamsalehy, Ruiyi Zhang, Sungchul Kim, Franck Dernoncourt, Nedim Lipka, Deonna Owens, and Jiuxiang Gu. 2025. Self-debiasing large language models: Zero-shot recognition and reduction of stereotypes. In Proce… find
  21. Deep Ganguli, Amanda Askell, Nicholas Schiefer, Thomas I. Liao, Kamilė Lukošiūtė, Anna Chen, Anna Goldie, Azalia Mirhoseini, Catherine Olsson, Danny Hernandez, Dawn Drain, Dustin Li, Eli Tran-Johnson, Ethan Perez, Jackson Kernion, Jamie Kerr, Jared Mueller, Joshua Landau, Kamal Ndousse, and 30 ot… — The Capacity for Moral Self-Correction in Large Language Models
  22. Jin X. Goh and Vlada Trofimchuk. 2023. Gendered perceptions of east and south asian men. Social Cognition, 41:537–561. find
  23. Haixia Han, Jiaqing Liang, Jie Shi, Qianyu He, and Yanghua Xiao. 2024. Small language model can self-correct. In Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence and Thirty-Sixth Conference on Innovative Applications of Artificial Intelligence and Fourteenth Symposium on E… find
  24. Chloe M. Harvey, Ingrid FitzGerald, Jo Sauvarin, Gerda Binder, and Karen Humphries-Waa. 2022. Premarital conception as a driver of child marriage and early union in selected countries in southeast asia and the pacific. Journal of Adolescent Health, 70(3, Supplement):S43–S46. Shared Roots, Different… find
  25. Nahid Hasan, Azaz Bin Sharif, Ishrat Jahan, and Mosammat Rashida Begum. 2023. Mental health status and the quality of life of infertile women receiving fertility treatment in bangladesh: A cross-sectional study. PLOS global public health, 3:e0002680– e0002680. find
  26. Matthew Honnibal, Ines Montani, Sofie Van Lan-deghem, and Adriane Boyd. 2020. spaCy: Industrial-strength Natural Language Processing in Python. find
  27. Hemalatha1 Jeyachandran, Aravindh Kumaran, L. Takhellambam Rocky Devi, D. Asokk, and Arun Prasad. 2019. Grocery shopping pattern of indian retail customers: Traditional stores vs. supermarkets. International Journal of Recent Technology and Engineering (IJRTE), 8:2055–2060. find
  28. Vamsee Juluri. 2020. “hindu nationalism” or “hindu-phobia”? find
  29. Khyati Khandelwal, Manuel Tonneau, Andrew M. Bean, Hannah Rose Kirk, and Scott A. Hale. 2024. Indian-bhed: A dataset for measuring india-centric biases in large language models. In Proceedings of the 2024 International Conference on Information Technology for Social Good, GoodIT ’24, page 231–239. A… find
  30. Elyakim Kislev. 2024. Singlehood as an identity. European Review of Social Psychology, 35(2):258–292. find
  31. Elyakim Kislev and Kris Marsh. 2010. Intersectionality in studying and theorizing singlehood. ArXiv preprint, abs/10.1111. find
  32. Loka Li, Zhenhao Chen, Guangyi Chen, Yixuan Zhang, Yusheng Su, Eric Xing, and Kun Zhang. 2024. Confidence matters: Revisiting intrinsic self-correction capabilities of large language models. ArXiv preprint, abs/2402.12563. — [arXiv:2402.12563](https://arxiv.org/abs/2402.12563) find
  33. Yinhan Liu, Jiatao Gu, Naman Goyal, Xian Li, Sergey Edunov, Marjan Ghazvininejad, Mike Lewis, and Luke Zettlemoyer. 2020. Multilingual denoising pre-training for neural machine translation. Transactions of the Association for Computational Linguistics, 8:726–742. find
  34. Tanzeela Mobeen and Saima Dawood. 2023. Relationship beliefs, attachment styles and depression among infertile women. European Journal Of Obstetrics & Gynecology And Reproductive Biology: X, 20:100245–100245. find
  35. Marta Mrozowicz-Wrońska, Kamil Janowicz, Emilia Soroko, and Katarzyna Adamczyk. 2023. Let’s talk about single men: A qualitative investigation of never married men’s experiences of singlehood. Sex Roles. find
  36. Niklas Muennighoff, Thomas Wang, Lintang Sutawika, Adam Roberts, Stella Biderman, Teven Le Scao, M Saiful Bari, Sheng Shen, Zheng-Xin Yong, Hailey Schoelkopf, and 1 others. 2022. Crosslingual generalization through multitask finetuning. ArXiv preprint, abs/2211.01786.
  37. Zubia Mumtaz, Umber Shahid, and Adrienne Levay. 2013. Understanding the impact of gendered roles on the experiences of infertility amongst men and women in punjab. Reproductive Health, 10. find
  38. Shuyo Nakatani. 2014. langdetect. Accessed: 2025-02-14. find
  39. Unaiza Niaz and Sehar Hassan. 2006. Culture and mental health of women in south-east asia. World psychiatry : official journal of the World Psychiatric Association (WPA), 5:118–20. find
  40. Bob Pierik. 2022. Patriarchal power as a conceptual tool for gender history. Rethinking History, 26(1):71–92. find
  41. Flor Miriam Plaza-del Arco, Amanda Cercas Curry, Susanna Paoli, Alba Curry, and Dirk Hovy. 2024. Divine LLaMAs: Bias, Stereotypes, Stigmatization, and Emotion Representation of Religion in Large Language Models. ArXiv preprint, abs/2407.06908. find
  42. Gowtham Ramesh, Sumanth Doddapaneni, Aravinth Bheemaraj, Mayank Jobanputra, Raghavan AK, Ajitesh Sharma, Sujit Sahoo, Harshita Diddee, Mahalakshmi J, Divyanshu Kakwani, Navneet Kumar, Aswin Pradeep, Srihari Nagaraj, Kumar Deepak, Vivek Raghavan, Anoop Kunchukuttan, Pratyush Kumar, and Mitesh Shantad… — Samanantar: The Largest Publicly Available Parallel Corpora Collection for 11 Indic Languages
  43. Priyanka Rathi. 2022. International journal of education and science research review “challenging stereotypes: The portrayal of masculinity in indian women’s literature". find
  44. Lisa Roberts, Solomon Renati, Shreeletha Solomon, and Susanne Montgomery. 2020. Women and infertility in a pronatalist culture: Mental health in the slums of mumbai\</p\>. International Journal of Women’s Health, Volume 12:993–1003. find
  45. Kanwal Rubab, Arif Alam, Noor Elahi, and Hamayun Khan. 2023. Gender-based adjustment problems of divorcees in hazara division, pakistan. PLOS ONE, 18:e0295068–e0295068. find
  46. Jayanta Sadhu, Maneesha Rani Saha, and Rifat Shahriyar. 2024. Social bias in large language models for bangla: An empirical study on gender and religious bias. ArXiv preprint, abs/2407.03536. find
  47. Nihar Ranjan Sahoo, Pranamya Prashant Kulkarni, Narjis Asad, Arif Ahmad, Tanu Goyal, Aparna Garimella, and Pushpak Bhattacharyya. 2024. Indibias: A benchmark dataset to measure social biases in language models for indian context. ArXiv preprint, abs/2403.20147. find
  48. Deepshikha Sahu. 2023. Purdah system. International Journal of Research Publication and Reviews Journal homepage: www.ijrpr.com, 4:5260–5262. find
  49. Claire Samtleben and Kai-Uwe Müller. 2022. Care and careers: Gender (in)equality in unpaid care, housework and employment. Research in Social Stratification and Mobility, 77:100659. find
  50. Sudipa Sarkar. 2024. Local crime and early marriage: Evidence from india. Journal of development studies, 60:763–787. find
  51. Yixin Wan and Kai-Wei Chang. 2024. White men lead, black women help? benchmarking language agency social biases in llms. ArXiv preprint, abs/2404.10508. — [arXiv:2404.10508](https://arxiv.org/abs/2404.10508) find
  52. Timo Schick, Sahana Udupa, and Hinrich Schütze. 2021. Self-diagnosis and self-debiasing: A proposal for reducing corpus-based bias in nlp. ArXiv preprint, abs/2103.00453.
  53. Samuel Scott, Phuong Hong Nguyen, Sumanta Neupane, Priyanjana Pramanik, Priya Nanda, Zulfiqar A. Bhutta, Kaosar Afsana, and Purnima Menon. 2021. Early marriage and early childbearing in south asia: trends, inequalities, and drivers from 2005 to 2018. Annals of the New York Academy of Sciences, 1491:… find
  54. Chandni Shah. 2016. South asian women’s sexual relationship power: Examining the role of sexism, cultural values conflict, discrimination, and social support. find
  55. Indira Sharma, Balram Pandit, Abhishek Pathak, and Reet Sharma. 2013. Hinduism, marriage and mental illness. Indian Journal of Psychiatry, 55:243. find
  56. John Sides and Kimberly Gross. 2013. Stereotypes of muslims and support for the war on terror. The Journal of Politics, 75(3):583–598. find
  57. Karen Sparck Jones. 1972. A statistical interpretation of term specificity and its application in retrieval. J. Doc., 28(1):11–21. find
  58. Keerthan Kumar T. G., Saish Mendke, Rohit Parihar, Samarth Mayya, Spoorthy Venkatesh, and Shashidhar G. Koolagudi. 2025. Dbnlp: detecting bias in natural language processing system for india-centric languages. International Journal of Information Technology. find
  59. Naznin Tabassum and Bhabani Shankar Nayak. 2021. Gender stereotypes and their impact on women’s career progressions from a managerial perspective. IIM Kozhikode Society & Management Review, 10(2):192– 208. find
  60. Joel Wester, Sander de Jong, Henning Pohl, and Niels van Berkel. 2024. Exploring people’s perceptions of llm-generated advice. Computers in Human Behavior: Artificial Humans, 2(2):100072. find
  61. Frank. Wilcoxon. 1945. Individual comparisons by ranking methods. Biometrics, 1:196–202. find
  62. Linting Xue, Noah Constant, Adam Roberts, Mihir Kale, Rami Al-Rfou, Aditya Siddhant, Aditya Barua, and Colin Raffel. 2021. mT5: A massively multilingual pre-trained text-to-text transformer. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Ling…
  63. Jieyu Zhao, Daniel Khashabi, Tushar Khot, Ashish Sabharwal, and Kai-Wei Chang. 2021. Ethical-advice taker: Do language models understand natural language interventions? In Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, pages 4158–4164, Online. Association for Computation… find
  64. Ahmet Üstün, Viraat Aryabumi, Zheng-Xin Yong, Wei-Yin Ko, Daniel D’souza, Gbemileke Onilude, Neel Bhandari, Shivalika Singh, Hui-Lee Ooi, Amr Kayid, Freddie Vargus, Phil Blunsom, Shayne Longpre, Niklas Muennighoff, Marzieh Fadaee, Julia Kreutzer, and Sara Hooker. 2024. Aya model: An instruction fine…

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/rinki-2026-purdah-patriarchy-evaluating-mitigating-south/