{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T10:56:25Z","timestamp":1783508185693,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":24,"publisher":"ACM","license":[{"start":{"date-parts":[[2019,1,27]],"date-time":"2019-01-27T00:00:00Z","timestamp":1548547200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-sa\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2019,1,27]]},"DOI":"10.1145\/3306618.3317950","type":"proceedings-article","created":{"date-parts":[[2019,7,10]],"date-time":"2019-07-10T12:10:59Z","timestamp":1562760659000},"page":"219-226","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":98,"title":["Counterfactual Fairness in Text Classification through Robustness"],"prefix":"10.1145","author":[{"given":"Sahaj","family":"Garg","sequence":"first","affiliation":[{"name":"Stanford University, Stanford, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vincent","family":"Perot","sequence":"additional","affiliation":[{"name":"Google AI, New York, NY, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nicole","family":"Limtiaco","sequence":"additional","affiliation":[{"name":"Google AI, New York, NY, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ankur","family":"Taly","sequence":"additional","affiliation":[{"name":"Google AI, Mountain View, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ed H.","family":"Chi","sequence":"additional","affiliation":[{"name":"Google AI, Mountain View, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alex","family":"Beutel","sequence":"additional","affiliation":[{"name":"Google AI, New York, NY, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2019,1,27]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Chi","author":"Beutel Alex","year":"2017","unstructured":"Alex Beutel , Jilin Chen , Zhe Zhao , and Ed H . Chi . 2017 . Data Decisions and Theoretical Implications when Adversarially Learning Fair Representations. CoRR , Vol. abs\/ 1707 .00075 (2017). arxiv: 1707.00075 http:\/\/arxiv.org\/abs\/1707.00075 Alex Beutel, Jilin Chen, Zhe Zhao, and Ed H. Chi. 2017. Data Decisions and Theoretical Implications when Adversarially Learning Fair Representations. CoRR, Vol. abs\/1707.00075 (2017). arxiv: 1707.00075 http:\/\/arxiv.org\/abs\/1707.00075"},{"key":"e_1_3_2_1_2_1","volume-title":"Gillam","author":"Chiappa Silvia","year":"2018","unstructured":"Silvia Chiappa and Thomas P. S . Gillam . 2018 . Path-Specific Counterfactual Fairness. arXiv e-prints, Article arXiv:1802.08139 (Feb. 2018), arXiv:1802.08139 pages. arxiv: stat.ML\/1802.08139 Silvia Chiappa and Thomas P. S. Gillam. 2018. Path-Specific Counterfactual Fairness. arXiv e-prints, Article arXiv:1802.08139 (Feb. 2018), arXiv:1802.08139 pages. arxiv: stat.ML\/1802.08139"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"crossref","unstructured":"Lucas Dixon John Li Jeffrey Sorensen Nithum Thain and Lucy Vasserman. 2018. Measuring and Mitigating Unintended Bias in Text Classification.  Lucas Dixon John Li Jeffrey Sorensen Nithum Thain and Lucy Vasserman. 2018. Measuring and Mitigating Unintended Bias in Text Classification.","DOI":"10.1145\/3278721.3278729"},{"key":"e_1_3_2_1_4_1","volume-title":"Zemel","author":"Dwork Cynthia","year":"2011","unstructured":"Cynthia Dwork , Moritz Hardt , Toniann Pitassi , Omer Reingold , and Richard S . Zemel . 2011 . Fairness Through Awareness. CoRR , Vol. abs\/ 1104 .3913 (2011). arxiv: 1104.3913 http:\/\/arxiv.org\/abs\/1104.3913 Cynthia Dwork, Moritz Hardt, Toniann Pitassi, Omer Reingold, and Richard S. Zemel. 2011. Fairness Through Awareness. CoRR, Vol. abs\/1104.3913 (2011). arxiv: 1104.3913 http:\/\/arxiv.org\/abs\/1104.3913"},{"key":"e_1_3_2_1_5_1","volume-title":"Explaining and Harnessing Adversarial Examples. In International Conference on Learning Representations. http:\/\/arxiv.org\/abs\/1412","author":"Goodfellow Ian","year":"2015","unstructured":"Ian Goodfellow , Jonathon Shlens , and Christian Szegedy . 2015 . Explaining and Harnessing Adversarial Examples. In International Conference on Learning Representations. http:\/\/arxiv.org\/abs\/1412 .6572 Ian Goodfellow, Jonathon Shlens, and Christian Szegedy. 2015. Explaining and Harnessing Adversarial Examples. In International Conference on Learning Representations. http:\/\/arxiv.org\/abs\/1412.6572"},{"key":"e_1_3_2_1_6_1","volume-title":"Equality of Opportunity in Supervised Learning. CoRR","author":"Hardt Moritz","year":"2016","unstructured":"Moritz Hardt , Eric Price , and Nathan Srebro . 2016. Equality of Opportunity in Supervised Learning. CoRR , Vol. abs\/ 1610 .02413 ( 2016 ). arxiv: 1610.02413 http:\/\/arxiv.org\/abs\/1610.02413 Moritz Hardt, Eric Price, and Nathan Srebro. 2016. Equality of Opportunity in Supervised Learning. CoRR, Vol. abs\/1610.02413 (2016). arxiv: 1610.02413 http:\/\/arxiv.org\/abs\/1610.02413"},{"key":"e_1_3_2_1_7_1","volume-title":"Proceedings of the 34th International Conference on Machine Learning (Proceedings of Machine Learning Research), Doina Precup and Yee Whye Teh (Eds.)","volume":"70","author":"Hu Zhiting","unstructured":"Zhiting Hu , Zichao Yang , Xiaodan Liang , Ruslan Salakhutdinov , and Eric P. Xing . 2017. Toward Controlled Generation of Text . In Proceedings of the 34th International Conference on Machine Learning (Proceedings of Machine Learning Research), Doina Precup and Yee Whye Teh (Eds.) , Vol. 70 . PMLR, International Convention Centre, Sydney, Australia, 1587--1596. http:\/\/proceedings.mlr.press\/v70\/hu17e.html Zhiting Hu, Zichao Yang, Xiaodan Liang, Ruslan Salakhutdinov, and Eric P. Xing. 2017. Toward Controlled Generation of Text. In Proceedings of the 34th International Conference on Machine Learning (Proceedings of Machine Learning Research), Doina Precup and Yee Whye Teh (Eds.), Vol. 70. PMLR, International Convention Centre, Sydney, Australia, 1587--1596. http:\/\/proceedings.mlr.press\/v70\/hu17e.html"},{"key":"e_1_3_2_1_8_1","volume-title":"Goodfellow","author":"Kannan Harini","year":"2018","unstructured":"Harini Kannan , Alexey Kurakin , and Ian J . Goodfellow . 2018 . Adversarial Logit Pairing. CoRR , Vol. abs\/ 1803 .06373 (2018). arxiv: 1803.06373 http:\/\/arxiv.org\/abs\/1803.06373 Harini Kannan, Alexey Kurakin, and Ian J. Goodfellow. 2018. Adversarial Logit Pairing. CoRR, Vol. abs\/1803.06373 (2018). arxiv: 1803.06373 http:\/\/arxiv.org\/abs\/1803.06373"},{"key":"e_1_3_2_1_9_1","volume-title":"Proceedings from the conference \"Neural Information Processing Systems","author":"Kilbertus N.","year":"2017","unstructured":"N. Kilbertus , M. Rojas-Carulla , G. Parascandolo , M. Hardt , D. Janzing , and B. Sch\u00f6lkopf . 2017. Avoiding Discrimination through Causal Reasoning . In Proceedings from the conference \"Neural Information Processing Systems 2017 . Curran Associates, Inc., 656--666. http:\/\/papers.nips.cc\/paper\/6668-avoiding-discrimination-through-causal-reasoning.pdf N. Kilbertus, M. Rojas-Carulla, G. Parascandolo, M. Hardt, D. Janzing, and B. Sch\u00f6lkopf. 2017. Avoiding Discrimination through Causal Reasoning. In Proceedings from the conference \"Neural Information Processing Systems 2017. Curran Associates, Inc., 656--666. http:\/\/papers.nips.cc\/paper\/6668-avoiding-discrimination-through-causal-reasoning.pdf"},{"key":"e_1_3_2_1_10_1","first-page":"5","article-title":"Eddie Murphy and the Dangers of Counterfactual Causal Thinking About Detecting Racial Discrimination","volume":"113","author":"Kohler-Hausmann Issa","year":"2019","unstructured":"Issa Kohler-Hausmann . 2019 . Eddie Murphy and the Dangers of Counterfactual Causal Thinking About Detecting Racial Discrimination . Northwestern University Law Review , Vol. 113 , 5 (Mar 2019). Issa Kohler-Hausmann. 2019. Eddie Murphy and the Dangers of Counterfactual Causal Thinking About Detecting Racial Discrimination. Northwestern University Law Review, Vol. 113, 5 (Mar 2019).","journal-title":"Northwestern University Law Review"},{"key":"e_1_3_2_1_11_1","volume-title":"Epidemiology","volume":"25","author":"Krieger Nancy","year":"2014","unstructured":"Nancy Krieger . 2014 . On the Causal Interpretation of Race . Epidemiology , Vol. 25 , 6 (2014). https:\/\/journals.lww.com\/epidem\/Fulltext\/2014\/11000\/On_the_Causal_Interpretation_of_Race.30.aspx Nancy Krieger. 2014. On the Causal Interpretation of Race. Epidemiology, Vol. 25, 6 (2014). https:\/\/journals.lww.com\/epidem\/Fulltext\/2014\/11000\/On_the_Causal_Interpretation_of_Race.30.aspx"},{"key":"e_1_3_2_1_12_1","first-page":"I","article-title":"Counterfactual Fairness","volume":"30","author":"Kusner Matt J","year":"2017","unstructured":"Matt J Kusner , Joshua Loftus , Chris Russell , and Ricardo Silva . 2017 . Counterfactual Fairness . In Advances in Neural Information Processing Systems 30 , I . Guyon, U. V. Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, and R. Garnett (Eds.). Curran Associates, Inc., 4066--4076. http:\/\/papers.nips.cc\/paper\/6995-counterfactual-fairness.pdf Matt J Kusner, Joshua Loftus, Chris Russell, and Ricardo Silva. 2017. Counterfactual Fairness. In Advances in Neural Information Processing Systems 30, I. Guyon, U. V. Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, and R. Garnett (Eds.). Curran Associates, Inc., 4066--4076. http:\/\/papers.nips.cc\/paper\/6995-counterfactual-fairness.pdf","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"crossref","unstructured":"Virgile Landeiro and Aron Culotta. 2016. Robust Text Classification in the Presence of Confounding Bias. https:\/\/www.aaai.org\/ocs\/index.php\/AAAI\/AAAI16\/paper\/view\/12445   Virgile Landeiro and Aron Culotta. 2016. Robust Text Classification in the Presence of Confounding Bias. https:\/\/www.aaai.org\/ocs\/index.php\/AAAI\/AAAI16\/paper\/view\/12445","DOI":"10.1609\/aaai.v30i1.9997"},{"key":"e_1_3_2_1_14_1","volume-title":"Zemel","author":"Louizos Christos","year":"2015","unstructured":"Christos Louizos , Kevin Swersky , Yujia Li , Max Welling , and Richard S . Zemel . 2015 . The Variational Fair Autoencoder. CoRR , Vol. abs\/ 1511 .00830 (2015). Christos Louizos, Kevin Swersky, Yujia Li, Max Welling, and Richard S. Zemel. 2015. The Variational Fair Autoencoder. CoRR, Vol. abs\/1511.00830 (2015)."},{"key":"e_1_3_2_1_15_1","volume-title":"Proceedings of the 1st Conference on Fairness, Accountability and Transparency (Proceedings of Machine Learning Research),, Sorelle A. Friedler and Christo Wilson (Eds.)","volume":"81","author":"Madaan Nishtha","year":"2018","unstructured":"Nishtha Madaan , Sameep Mehta , Taneea Agrawaal , Vrinda Malhotra , Aditi Aggarwal , Yatin Gupta , and Mayank Saxena . 2018 . Analyze, Detect and Remove Gender Stereotyping from Bollywood Movies . In Proceedings of the 1st Conference on Fairness, Accountability and Transparency (Proceedings of Machine Learning Research),, Sorelle A. Friedler and Christo Wilson (Eds.) , Vol. 81 . PMLR, New York, NY, USA, 92--105. http:\/\/proceedings.mlr.press\/v81\/madaan18a.html Nishtha Madaan, Sameep Mehta, Taneea Agrawaal, Vrinda Malhotra, Aditi Aggarwal, Yatin Gupta, and Mayank Saxena. 2018. Analyze, Detect and Remove Gender Stereotyping from Bollywood Movies. In Proceedings of the 1st Conference on Fairness, Accountability and Transparency (Proceedings of Machine Learning Research),, Sorelle A. Friedler and Christo Wilson (Eds.), Vol. 81. PMLR, New York, NY, USA, 92--105. http:\/\/proceedings.mlr.press\/v81\/madaan18a.html"},{"key":"e_1_3_2_1_16_1","volume-title":"Towards Deep Learning Models Resistant to Adversarial Attacks. CoRR","author":"Madry Aleksander","year":"2017","unstructured":"Aleksander Madry , Aleksandar Makelov , Ludwig Schmidt , Dimitris Tsipras , and Adrian Vladu . 2017. Towards Deep Learning Models Resistant to Adversarial Attacks. CoRR , Vol. abs\/ 1706 .06083 ( 2017 ). arxiv: 1706.06083 http:\/\/arxiv.org\/abs\/1706.06083 Aleksander Madry, Aleksandar Makelov, Ludwig Schmidt, Dimitris Tsipras, and Adrian Vladu. 2017. Towards Deep Learning Models Resistant to Adversarial Attacks. CoRR, Vol. abs\/1706.06083 (2017). arxiv: 1706.06083 http:\/\/arxiv.org\/abs\/1706.06083"},{"key":"e_1_3_2_1_17_1","volume-title":"Did the Model Understand the Question? CoRR","author":"Mudrakarta Pramod Kaushik","year":"2018","unstructured":"Pramod Kaushik Mudrakarta , Ankur Taly , Mukund Sundararajan , and Kedar Dhamdhere . 2018. Did the Model Understand the Question? CoRR , Vol. abs\/ 1805 .05492 ( 2018 ). Pramod Kaushik Mudrakarta, Ankur Taly, Mukund Sundararajan, and Kedar Dhamdhere. 2018. Did the Model Understand the Question? CoRR, Vol. abs\/1805.05492 (2018)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"crossref","unstructured":"J. H. Park J. Shin and P. Fung. 2018. Reducing Gender Bias in Abusive Language Detection. ArXiv e-prints (Aug. 2018). arxiv: cs.CL\/1808.07231  J. H. Park J. Shin and P. Fung. 2018. Reducing Gender Bias in Abusive Language Detection. ArXiv e-prints (Aug. 2018). arxiv: cs.CL\/1808.07231","DOI":"10.18653\/v1\/D18-1302"},{"key":"e_1_3_2_1_19_1","volume-title":"Deconfounded Lexicon Induction for Interpretable Social Science. In 16th Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL) .","author":"Pryzant Reid","year":"2018","unstructured":"Reid Pryzant , Kelly Wang , Dan Jurafsky , and Stefan Wager . 2018 . Deconfounded Lexicon Induction for Interpretable Social Science. In 16th Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL) . Reid Pryzant, Kelly Wang, Dan Jurafsky, and Stefan Wager. 2018. Deconfounded Lexicon Induction for Interpretable Social Science. In 16th Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL) ."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1079"},{"key":"e_1_3_2_1_21_1","volume-title":"Robinson","author":"VanderWeele Tyler J.","year":"2014","unstructured":"Tyler J. VanderWeele and Whitney R . Robinson . 2014 . On the Causal Interpretation of Race. Epidemiology , Vol. 25 , 6 (2014). https:\/\/journals.lww.com\/epidem\/Fulltext\/2014\/11000\/On_the_Causal_Interpretation_of_Race.31.aspx Tyler J. VanderWeele and Whitney R. Robinson. 2014. On the Causal Interpretation of Race. Epidemiology, Vol. 25, 6 (2014). https:\/\/journals.lww.com\/epidem\/Fulltext\/2014\/11000\/On_the_Causal_Interpretation_of_Race.31.aspx"},{"key":"e_1_3_2_1_22_1","volume-title":"Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPR. CoRR","author":"Wachter Sandra","year":"2017","unstructured":"Sandra Wachter , Brent D. Mittelstadt , and Chris Russell . 2017. Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPR. CoRR , Vol. abs\/ 1711 .00399 ( 2017 ). Sandra Wachter, Brent D. Mittelstadt, and Chris Russell. 2017. Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPR. CoRR, Vol. abs\/1711.00399 (2017)."},{"key":"e_1_3_2_1_23_1","volume-title":"Proceedings of the 30th International Conference on Machine Learning (Proceedings of Machine Learning Research), Sanjoy Dasgupta and David McAllester (Eds.)","volume":"28","author":"Zemel Rich","year":"2013","unstructured":"Rich Zemel , Yu Wu , Kevin Swersky , Toni Pitassi , and Cynthia Dwork . 2013 . Learning Fair Representations . In Proceedings of the 30th International Conference on Machine Learning (Proceedings of Machine Learning Research), Sanjoy Dasgupta and David McAllester (Eds.) , Vol. 28 . PMLR, Atlanta, Georgia, USA, 325--333. http:\/\/proceedings.mlr.press\/v28\/zemel13.html Rich Zemel, Yu Wu, Kevin Swersky, Toni Pitassi, and Cynthia Dwork. 2013. Learning Fair Representations. In Proceedings of the 30th International Conference on Machine Learning (Proceedings of Machine Learning Research), Sanjoy Dasgupta and David McAllester (Eds.), Vol. 28. PMLR, Atlanta, Georgia, USA, 325--333. http:\/\/proceedings.mlr.press\/v28\/zemel13.html"},{"key":"e_1_3_2_1_24_1","volume-title":"Generating Natural Adversarial Examples. CoRR","author":"Zhao Zhengli","year":"2017","unstructured":"Zhengli Zhao , Dheeru Dua , and Sameer Singh . 2017. Generating Natural Adversarial Examples. CoRR , Vol. abs\/ 1710 .11342 ( 2017 ). Zhengli Zhao, Dheeru Dua, and Sameer Singh. 2017. Generating Natural Adversarial Examples. CoRR, Vol. abs\/1710.11342 (2017)."}],"event":{"name":"AIES '19: AAAI\/ACM Conference on AI, Ethics, and Society","location":"Honolulu HI USA","acronym":"AIES '19","sponsor":["SIGAI ACM Special Interest Group on Artificial Intelligence","AAAI American Association for Artificial Intelligence"]},"container-title":["Proceedings of the 2019 AAAI\/ACM Conference on AI, Ethics, and Society"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3306618.3317950","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3306618.3317950","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T01:02:04Z","timestamp":1750208524000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3306618.3317950"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,1,27]]},"references-count":24,"alternative-id":["10.1145\/3306618.3317950","10.1145\/3306618"],"URL":"https:\/\/doi.org\/10.1145\/3306618.3317950","relation":{},"subject":[],"published":{"date-parts":[[2019,1,27]]},"assertion":[{"value":"2019-01-27","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}