{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T19:45:05Z","timestamp":1782762305931,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":44,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T00:00:00Z","timestamp":1782345600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/100007631","name":"Canadian Institute for Advanced Research","doi-asserted-by":"publisher","award":["CIFAR AI Chair Program"],"award-info":[{"award-number":["CIFAR AI Chair Program"]}],"id":[{"id":"10.13039\/100007631","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000038","name":"Natural Sciences and Engineering Research Council of Canada","doi-asserted-by":"publisher","award":["DGECR-2021-00279"],"award-info":[{"award-number":["DGECR-2021-00279"]}],"id":[{"id":"10.13039\/501100000038","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,6,25]]},"DOI":"10.1145\/3805689.3812330","type":"proceedings-article","created":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T17:52:08Z","timestamp":1782755528000},"page":"3858-3879","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["RobustDebias: Debiasing Language Models using Distributionally Robust Optimization"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7940-112X","authenticated-orcid":false,"given":"Deep","family":"Gandhi","sequence":"first","affiliation":[{"name":"University of Alberta, Edmonton, Canada, and Alberta Machine Intelligence Institute, Edmonton, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-2232-019X","authenticated-orcid":false,"given":"Katyani","family":"Singh","sequence":"additional","affiliation":[{"name":"University of Alberta, Edmonton, Canada, and Alberta Machine Intelligence Institute, Edmonton, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7385-3416","authenticated-orcid":false,"given":"Nidhi","family":"Hegde","sequence":"additional","affiliation":[{"name":"University of Alberta, Edmonton, Canada, Alberta Machine Intelligence Institute, edmonton, Canada, and CIFAR AI Chair, Edmonton, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,6,25]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"David Dale, Ning Dong, Paul-Ambroise Duquenne, Hady Elsahar, Hongyu Gong, Kevin Heffernan, John Hoffman, et al.","author":"Barrault Lo\u00efc","year":"2023","unstructured":"Lo\u00efc Barrault, Yu-An Chung, Mariano Cora Meglioli, David Dale, Ning Dong, Paul-Ambroise Duquenne, Hady Elsahar, Hongyu Gong, Kevin Heffernan, John Hoffman, et al. 2023. SeamlessM4T-Massively Multilingual & Multimodal Machine Translation. arXiv preprint arXiv:2308.11596 (2023)."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.1120.1641"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.81"},{"key":"e_1_3_2_1_4_1","volume-title":"Man is to computer programmer as woman is to homemaker? debiasing word embeddings. Advances in neural information processing systems 29","author":"Bolukbasi Tolga","year":"2016","unstructured":"Tolga Bolukbasi, Kai-Wei Chang, James Y Zou, Venkatesh Saligrama, and Adam T Kalai. 2016. Man is to computer programmer as woman is to homemaker? debiasing word embeddings. Advances in neural information processing systems 29 (2016). https:\/\/arxiv.org\/pdf\/1607.06520.pdf"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.139"},{"key":"e_1_3_2_1_6_1","volume-title":"Lin (Eds.)","volume":"33","author":"Brown Tom","year":"2020","unstructured":"Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, Sandhini Agarwal, Ariel Herbert-Voss, Gretchen Krueger, Tom Henighan, Rewon Child, Aditya Ramesh, Daniel Ziegler, Jeffrey Wu, Clemens Winter, Chris Hesse, Mark Chen, Eric Sigler, Mateusz Litwin, Scott Gray, Benjamin Chess, Jack Clark, Christopher Berner, Sam McCandlish, Alec Radford, Ilya Sutskever, and Dario Amodei. 2020. Language Models are Few-Shot Learners. In Advances in Neural Information Processing Systems, H. Larochelle, M. Ranzato, R. Hadsell, M.F. Balcan, and H. Lin (Eds.), Vol. 33. Curran Associates, Inc., 1877\u20131901. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2020\/file\/1457c0d6bfcb4967418bfb8ac142f64a-Paper.pdf"},{"key":"e_1_3_2_1_7_1","volume-title":"Semantics derived automatically from language corpora contain human-like biases. Science 356, 6334","author":"Caliskan Aylin","year":"2017","unstructured":"Aylin Caliskan, Joanna J Bryson, and Arvind Narayanan. 2017. Semantics derived automatically from language corpora contain human-like biases. Science 356, 6334 (2017), 183\u2013186."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-2029"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3287560.3287572"},{"key":"e_1_3_2_1_10_1","volume-title":"Proceedings of the 2019 conference of the North American chapter of the association for computational linguistics: human language technologies","volume":"1","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. Bert: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 conference of the North American chapter of the association for computational linguistics: human language technologies, volume 1 (long and short papers). 4171\u20134186."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1037\/0022-3514.82.1.62"},{"key":"e_1_3_2_1_12_1","unstructured":"Leo Gao Stella Biderman Sid Black Laurence Golding Travis Hoppe Charles Foster Jason Phang Horace He Anish Thite Noa Nabeshima et al. 2020. The pile: An 800gb dataset of diverse text for language modeling. arXiv preprint arXiv:2101.00027 (2020)."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.72"},{"key":"e_1_3_2_1_14_1","unstructured":"Zishan Guo Renren Jin Chuang Liu Yufei Huang Dan Shi Linhao Yu Yan Liu Jiaxuan Li Bojian Xiong Deyi Xiong et al. 2023. Evaluating large language models: A comprehensive survey. arXiv preprint arXiv:2310.19736 (2023)."},{"key":"e_1_3_2_1_15_1","volume-title":"Universal language model fine-tuning for text classification. arXiv preprint arXiv:1801.06146","author":"Howard Jeremy","year":"2018","unstructured":"Jeremy Howard and Sebastian Ruder. 2018. Universal language model fine-tuning for text classification. arXiv preprint arXiv:1801.06146 (2018)."},{"key":"e_1_3_2_1_16_1","volume-title":"Proceedings of the Twenty Third International Conference on Artificial Intelligence and Statistics (Proceedings of Machine Learning Research","volume":"679","author":"Kawaguchi Kenji","year":"2020","unstructured":"Kenji Kawaguchi and Haihao Lu. 2020. Ordered SGD: A New Stochastic Optimization Framework for Empirical Risk Minimization. In Proceedings of the Twenty Third International Conference on Artificial Intelligence and Statistics (Proceedings of Machine Learning Research, Vol. 108), Silvia Chiappa and Roberto Calandra (Eds.). PMLR, 669\u2013679. https:\/\/proceedings.mlr.press\/v108\/kawaguchi20a.html"},{"key":"e_1_3_2_1_17_1","volume-title":"Albert: A lite bert for self-supervised learning of language representations. arXiv preprint arXiv:1909.11942","author":"Lan Zhenzhong","year":"2019","unstructured":"Zhenzhong Lan, Mingda Chen, Sebastian Goodman, Kevin Gimpel, Piyush Sharma, and Radu Soricut. 2019. Albert: A lite bert for self-supervised learning of language representations. arXiv preprint arXiv:1909.11942 (2019). https:\/\/arxiv.org\/pdf\/1909.11942.pdf"},{"key":"e_1_3_2_1_18_1","first-page":"8847","article-title":"Large-scale methods for distributionally robust optimization","volume":"33","author":"Levy Daniel","year":"2020","unstructured":"Daniel Levy, Yair Carmon, John C Duchi, and Aaron Sidford. 2020. Large-scale methods for distributionally robust optimization. Advances in Neural Information Processing Systems 33 (2020), 8847\u20138860. https:\/\/arxiv.org\/pdf\/2010.05893.pdf","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_19_1","volume-title":"Emily Zheng, Yao Chong Lim, Ruslan Salakhutdinov, and Louis-Philippe Morency.","author":"Liang Paul Pu","year":"2020","unstructured":"Paul Pu Liang, Irene Mengze Li, Emily Zheng, Yao Chong Lim, Ruslan Salakhutdinov, and Louis-Philippe Morency. 2020. Towards debiasing sentence representations. arXiv preprint arXiv:2007.08100 (2020)."},{"key":"e_1_3_2_1_20_1","volume-title":"Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692","author":"Liu Yinhan","year":"2019","unstructured":"Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692 (2019). https:\/\/arxiv.org\/pdf\/1907.11692.pdf"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1063"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.132"},{"key":"e_1_3_2_1_23_1","volume-title":"Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781","author":"Mikolov Tomas","year":"2013","unstructured":"Tomas Mikolov, Kai Chen, Greg Corrado, and Jeffrey Dean. 2013. Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781 (2013)."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.416"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.154"},{"key":"e_1_3_2_1_26_1","volume-title":"Distributionally robust language modeling. arXiv preprint arXiv:1909.02060","author":"Oren Yonatan","year":"2019","unstructured":"Yonatan Oren, Shiori Sagawa, Tatsunori B Hashimoto, and Percy Liang. 2019. Distributionally robust language modeling. arXiv preprint arXiv:1909.02060 (2019)."},{"key":"e_1_3_2_1_27_1","volume-title":"Automatic Differentiation in PyTorch. In NIPS 2017 Workshop on Autodiff","author":"Paszke Adam","year":"2017","unstructured":"Adam Paszke, Sam Gross, Soumith Chintala, Gregory Chanan, Edward Yang, Zachary DeVito, Zeming Lin, Alban Desmaison, Luca Antiga, and Adam Lerer. 2017. Automatic Differentiation in PyTorch. In NIPS 2017 Workshop on Autodiff (Long Beach, California, USA). https:\/\/openreview.net\/forum?id=BJJsrmfCZ"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3600211.3604712"},{"key":"e_1_3_2_1_29_1","volume-title":"Null it out: Guarding protected attributes by iterative nullspace projection. arXiv preprint arXiv:2004.07667","author":"Ravfogel Shauli","year":"2020","unstructured":"Shauli Ravfogel, Yanai Elazar, Hila Gonen, Michael Twiton, and Yoav Goldberg. 2020. Null it out: Guarding protected attributes by iterative nullspace projection. arXiv preprint arXiv:2004.07667 (2020)."},{"key":"e_1_3_2_1_30_1","volume-title":"Distributionally Robust Neural Networks. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=ryxGuJrFvS","author":"Sagawa Shiori","year":"2020","unstructured":"Shiori Sagawa, Pang Wei Koh, Tatsunori B. Hashimoto, and Percy Liang. 2020. Distributionally Robust Neural Networks. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=ryxGuJrFvS"},{"key":"e_1_3_2_1_31_1","volume-title":"a distilled version of BERT: smaller, faster, cheaper and lighter. arXiv preprint arXiv:1910.01108","author":"Sanh Victor","year":"2019","unstructured":"Victor Sanh, Lysandre Debut, Julien Chaumond, and Thomas Wolf. 2019. DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter. arXiv preprint arXiv:1910.01108 (2019). https:\/\/arxiv.org\/pdf\/1910.01108.pdf"},{"key":"e_1_3_2_1_32_1","volume-title":"FineDeb: A Debiasing Framework for Language Models. arXiv preprint arXiv:2302.02453","author":"Saravanan Akash","year":"2023","unstructured":"Akash Saravanan, Dhruv Mullick, Habibur Rahman, and Nidhi Hegde. 2023. FineDeb: A Debiasing Framework for Language Models. arXiv preprint arXiv:2302.02453 (2023). https:\/\/arxiv.org\/pdf\/2302.02453.pdf"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.625"},{"key":"e_1_3_2_1_34_1","unstructured":"Hugo Touvron Louis Martin Kevin Stone Peter Albert Amjad Almahairi Yasmine Babaei Nikolay Bashlykov Soumya Batra Prajjwal Bhargava Shruti Bhosale et al. 2023. Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00335"},{"key":"e_1_3_2_1_36_1","first-page":"2579","article-title":"Visualizing Data using t-SNE","volume":"9","author":"van der Maaten Laurens","year":"2008","unstructured":"Laurens van der Maaten and Geoffrey Hinton. 2008. Visualizing Data using t-SNE. Journal of Machine Learning Research 9, 86 (2008), 2579\u20132605. http:\/\/jmlr.org\/papers\/v9\/vandermaaten08a.html","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_1_37_1","volume-title":"\u0141 ukasz Kaiser, and Illia Polosukhin","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141 ukasz Kaiser, and Illia Polosukhin. 2017. Attention is All you Need. In Advances in Neural Information Processing Systems, I. Guyon, U. Von Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, and R. Garnett (Eds.), Vol. 30. Curran Associates, Inc. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2017\/file\/3f5ee243547dee91fbd053c1c4a845aa-Paper.pdf"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-5446"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"e_1_3_2_1_40_1","volume-title":"DoReMi: Optimizing Data Mixtures Speeds Up Language Model Pretraining. arXiv preprint arXiv:2305.10429","author":"Xie Sang Michael","year":"2023","unstructured":"Sang Michael Xie, Hieu Pham, Xuanyi Dong, Nan Du, Hanxiao Liu, Yifeng Lu, Percy Liang, Quoc V Le, Tengyu Ma, and Adams Wei Yu. 2023. DoReMi: Optimizing Data Mixtures Speeds Up Language Model Pretraining. arXiv preprint arXiv:2305.10429 (2023). https:\/\/arxiv.org\/pdf\/2305.10429.pdf"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.375"},{"key":"e_1_3_2_1_42_1","volume-title":"Learning gender-neutral word embeddings. arXiv preprint arXiv:1809.01496","author":"Zhao Jieyu","year":"2018","unstructured":"Jieyu Zhao, Yichao Zhou, Zeyu Li, Wei Wang, and Kai-Wei Chang. 2018. Learning gender-neutral word embeddings. arXiv preprint arXiv:1809.01496 (2018)."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.232"},{"key":"e_1_3_2_1_44_1","volume-title":"Counterfactual data augmentation for mitigating gender stereotypes in languages with rich morphology. arXiv preprint arXiv:1906.04571","author":"Zmigrod Ran","year":"2019","unstructured":"Ran Zmigrod, Sabrina J Mielke, Hanna Wallach, and Ryan Cotterell. 2019. Counterfactual data augmentation for mitigating gender stereotypes in languages with rich morphology. arXiv preprint arXiv:1906.04571 (2019)."}],"event":{"name":"FAccT '26: The 2026 ACM Conference on Fairness, Accountability, and Transparency","location":"Montreal QC Canada","acronym":"FAccT '26","sponsor":["ACM\/SIG"]},"container-title":["Proceedings of the 2026 ACM Conference on Fairness, Accountability, and Transparency"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3805689.3812330","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T18:59:48Z","timestamp":1782759588000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3805689.3812330"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,25]]},"references-count":44,"alternative-id":["10.1145\/3805689.3812330","10.1145\/3805689"],"URL":"https:\/\/doi.org\/10.1145\/3805689.3812330","relation":{},"subject":[],"published":{"date-parts":[[2026,6,25]]},"assertion":[{"value":"2026-06-25","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}