{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T06:32:43Z","timestamp":1782801163443,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":74,"publisher":"ACM","funder":[{"DOI":"10.13039\/100000010","name":"Ford Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000010","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,11,5]]},"DOI":"10.1145\/3757887.3763010","type":"proceedings-article","created":{"date-parts":[[2025,10,29]],"date-time":"2025-10-29T07:42:58Z","timestamp":1761723778000},"page":"185-217","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Identity-related Speech Suppression in Generative AI Content Moderation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-4330-640X","authenticated-orcid":false,"given":"Grace","family":"Proebsting","sequence":"first","affiliation":[{"name":"Haverford College, Haverford, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-8976-3131","authenticated-orcid":false,"given":"Oghenefejiro Isaacs","family":"Anigboro","sequence":"additional","affiliation":[{"name":"Haverford College, Haverford, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-3955-0316","authenticated-orcid":false,"given":"Charlie M.","family":"Crawford","sequence":"additional","affiliation":[{"name":"Haverford College, Haverford, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9359-6090","authenticated-orcid":false,"given":"Dana\u00e9","family":"Metaxa","sequence":"additional","affiliation":[{"name":"University of Pennsylvania, Philadelphia, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6023-1597","authenticated-orcid":false,"given":"Sorelle A.","family":"Friedler","sequence":"additional","affiliation":[{"name":"Haverford College, Haverford, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,11,4]]},"reference":[{"key":"e_1_3_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1145\/3461702.3462624"},{"key":"e_1_3_3_2_3_2","doi-asserted-by":"crossref","unstructured":"Hammaad Adam Aparna Balagopalan Emily Alsentzer Fotini Christia and Marzyeh Ghassemi. 2022. Mitigating the impact of biased artificial intelligence in emergency decision-making. Communications Medicine 2 1 (2022) 149.","DOI":"10.1038\/s43856-022-00214-4"},{"key":"e_1_3_3_2_4_2","unstructured":"Anthropic. 2024. Anthropic Cookbook: Building a moderation filter with Claude. https:\/\/github.com\/anthropics\/anthropic-cookbook\/blob\/main\/misc\/building_moderation_filter.ipynb."},{"key":"e_1_3_3_2_5_2","unstructured":"Anthropic. 2024. Consumer Terms of Service. https:\/\/www.anthropic.com\/legal\/consumer-terms."},{"key":"e_1_3_3_2_6_2","doi-asserted-by":"crossref","unstructured":"Lena Armstrong Abbey Liu Stephen MacNeil and Dana\u00eb Metaxa. 2024. The Silicon Ceiling: Auditing GPT\u2019s Race and Gender Biases in Hiring. EEAMO (2024).","DOI":"10.1145\/3689904.3694699"},{"key":"e_1_3_3_2_7_2","unstructured":"Motion\u00a0Picture Association. 2020. CLASSIFICATION AND RATING RULES. https:\/\/www.filmratings.com\/Content\/Downloads\/rating_rules.pdf."},{"key":"e_1_3_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1145\/3628516.3659404"},{"key":"e_1_3_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.148"},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"crossref","unstructured":"Gonzalo\u00a0Molpeceres Barrientos Roc\u00edo Alaiz-Rodr\u00edguez V\u00edctor Gonz\u00e1lez-Castro and Andrew\u00a0C Parnell. 2020. Machine learning techniques for the detection of inappropriate erotic content in text. International Journal of Computational Intelligence Systems 13 1 (2020) 591\u2013603.","DOI":"10.2991\/ijcis.d.200519.003"},{"key":"e_1_3_3_2_11_2","volume-title":"Dyles to Watch Out For","author":"Bechdel Alison","year":"1985","unstructured":"Alison Bechdel. 1985. Dyles to Watch Out For. Chapter The Rule. https:\/\/dykestowatchoutfor.com\/the-rule\/."},{"key":"e_1_3_3_2_12_2","unstructured":"Joe Biden. 2023. Safe Secure and Trustworthy Development and Use of Artificial Intelligence. Executive Order 14110."},{"key":"e_1_3_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-67256-4_32"},{"key":"e_1_3_3_2_14_2","unstructured":"Tolga Bolukbasi Kai-Wei Chang James\u00a0Y Zou Venkatesh Saligrama and Adam\u00a0T Kalai. 2016. Man is to computer programmer as woman is to homemaker? debiasing word embeddings. Advances in neural information processing systems 29 (2016)."},{"key":"e_1_3_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1145\/3308560.3317593"},{"key":"e_1_3_3_2_16_2","unstructured":"Thomas Brewster. 2025. Pedophiles Are Using AI To Turn Children\u2019s Social Media Photos Into CSAM. Forbes (April 8 2025)."},{"key":"e_1_3_3_2_17_2","unstructured":"Tom Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared\u00a0D Kaplan Prafulla Dhariwal Arvind Neelakantan Pranav Shyam Girish Sastry Amanda Askell et\u00a0al. 2020. Language models are few-shot learners. Advances in neural information processing systems 33 (2020) 1877\u20131901."},{"key":"e_1_3_3_2_18_2","doi-asserted-by":"crossref","unstructured":"Aylin Caliskan Joanna\u00a0J Bryson and Arvind Narayanan. 2017. Semantics derived automatically from language corpora contain human-like biases. Science 356 6334 (2017) 183\u2013186.","DOI":"10.1126\/science.aal4230"},{"key":"e_1_3_3_2_19_2","doi-asserted-by":"crossref","unstructured":"Kaylea Champion and Benjamin\u00a0Mako Hill. 2023. Taboo and Collaborative Knowledge Production: Evidence from Wikipedia. Proceedings of the ACM on Human-Computer Interaction 7 CSCW2 (2023) 1\u201325.","DOI":"10.1145\/3610090"},{"key":"e_1_3_3_2_20_2","doi-asserted-by":"crossref","unstructured":"Crystal\u00a0T Chang Hodan Farah Haiwen Gui Shawheen\u00a0Justin Rezaei Charbel Bou-Khalil Ye-Jean Park Akshay Swaminathan Jesutofunmi\u00a0A Omiye Akaash Kolluri Akash Chaurasia et\u00a0al. 2025. Red teaming ChatGPT in medicine to yield real-world insights on model behavior. npj Digital Medicine 8 1 (2025) 149.","DOI":"10.1038\/s41746-025-01542-0"},{"key":"e_1_3_3_2_21_2","unstructured":"cjadams Daniel Borkan inversion Jeffrey Sorensen Lucas Dixon Lucy Vasserman and nithum.2019. Jigsaw Unintended Bias in Toxicity Classification. Kaggle https:\/\/kaggle.com\/competitions\/jigsaw-unintended-bias-in-toxicity-classification."},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1609\/icwsm.v11i1.14955"},{"key":"e_1_3_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-5102"},{"key":"e_1_3_3_2_24_2","unstructured":"\u00c1ngel D\u00edaz and Laura Hecht-Felella. 2021. Double standards in social media content moderation. Brennan Center for Justice at New York University School of Law (2021) 1\u201323."},{"key":"e_1_3_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1145\/3278721.3278729"},{"key":"e_1_3_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.507"},{"key":"e_1_3_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1145\/3593013.3594094"},{"key":"e_1_3_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1145\/3287560.3287589"},{"key":"e_1_3_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.301"},{"key":"e_1_3_3_2_30_2","doi-asserted-by":"crossref","unstructured":"Tarleton Gillespie. 2024. Generative AI and the politics of visibility. Big Data & Society 11 2 (2024) 20539517241252131.","DOI":"10.1177\/20539517241252131"},{"key":"e_1_3_3_2_31_2","doi-asserted-by":"publisher","unstructured":"Amy Gonzales Dana Mastro Laurent Wang Jeannine Bell Philip Anderson and Jelani Ince. 2021. Dis\"Like\": How Race and Education May Influence the Perceived Costs of Internet Use in the U.S. Proc. ACM Hum.-Comput. Interact. 5 CSCW1 Article 57 (April 2021) 19\u00a0pages. 10.1145\/3449131https:\/\/doi.org\/10.1145\/3449131.","DOI":"10.1145\/3449131"},{"key":"e_1_3_3_2_32_2","unstructured":"Google. 2024. Google Cloud: Moderate text. https:\/\/cloud.google.com\/natural-language\/docs\/moderating-text."},{"key":"e_1_3_3_2_33_2","doi-asserted-by":"crossref","unstructured":"Nitesh Goyal Ian\u00a0D Kivlichan Rachel Rosen and Lucy Vasserman. 2022. Is your toxicity my toxicity? exploring the impact of rater identity on toxicity annotation. Proceedings of the ACM on Human-Computer Interaction 6 CSCW2 (2022) 1\u201328.","DOI":"10.1145\/3555088"},{"key":"e_1_3_3_2_34_2","volume-title":"Ghost work: How to stop Silicon Valley from building a new global underclass","author":"Gray Mary\u00a0L","year":"2019","unstructured":"Mary\u00a0L Gray and Siddharth Suri. 2019. Ghost work: How to stop Silicon Valley from building a new global underclass. Harper Business."},{"key":"e_1_3_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/CBMI.2019.8877435"},{"key":"e_1_3_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1145\/3706598.3713998"},{"key":"e_1_3_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.487"},{"key":"e_1_3_3_2_38_2","unstructured":"Hakan Inan Kartikeya Upasani Jianfeng Chi Rashi Rungta Krithika Iyer Yuning Mao Michael Tontchev Qing Hu Brian Fuller Davide Testuggine et\u00a0al. 2023. Llama guard: Llm-based input-output safeguard for human-ai conversations. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2312.06674 (2023)."},{"key":"e_1_3_3_2_39_2","doi-asserted-by":"crossref","unstructured":"Deanna\u00a0M Kaplan Roman Palitsky Santiago\u00a0J Arconada\u00a0Alvarez Nicole\u00a0S Pozzo Morgan\u00a0N Greenleaf Ciara\u00a0A Atkinson and Wilbur\u00a0A Lam. 2024. What\u2019s in a Name? Experimental Evidence of Gender Bias in Recommendation Letters Generated by ChatGPT. Journal of Medical Internet Research 26 (2024) e51837.","DOI":"10.2196\/51837"},{"key":"e_1_3_3_2_40_2","unstructured":"Molly Kinder. 2024. Hollywood writers went on strike to protect their livelihoods from generative AI. Their remarkable victory matters for all workers. Brookings (April 12 2024)."},{"key":"e_1_3_3_2_41_2","unstructured":"Nicole Kobie. 2023. AI Is Telling Bedtime Stories to Your Kids Now: Artificial intelligence can now tell tales featuring your kids\u2019 favorite characters. It\u2019s copyright chaos-and a major headache for parents and guardians. Wired (December 24 2023)."},{"key":"e_1_3_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642278"},{"key":"e_1_3_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v27i1.8539"},{"key":"e_1_3_3_2_44_2","doi-asserted-by":"crossref","unstructured":"Michelle\u00a0S Lam Mitchell\u00a0L Gordon Dana\u00eb Metaxa Jeffrey\u00a0T Hancock James\u00a0A Landay and Michael\u00a0S Bernstein. 2022. End-user audits: A system empowering communities to lead large-scale investigations of harmful algorithmic behavior. proceedings of the ACM on Human-Computer Interaction 6 CSCW2 (2022) 1\u201334.","DOI":"10.1145\/3555625"},{"key":"e_1_3_3_2_45_2","doi-asserted-by":"crossref","unstructured":"Louis Lippens. 2024. Computer says \u2018no\u2019: Exploring systemic bias in ChatGPT using an audit approach. Computers in Human Behavior: Artificial Humans 2 1 (2024) 100054.","DOI":"10.1016\/j.chbah.2024.100054"},{"key":"e_1_3_3_2_46_2","doi-asserted-by":"publisher","DOI":"10.1145\/3689904.3694709"},{"key":"e_1_3_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.1145\/3630106.3658932"},{"key":"e_1_3_3_2_48_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDMW60847.2023.00037"},{"key":"e_1_3_3_2_49_2","doi-asserted-by":"publisher","unstructured":"Todor Markov Chong Zhang Sandhini Agarwal Florentine Eloundou\u00a0Nekoul Theodore Lee Steven Adler Angela Jiang and Lilian Weng. 2023. A Holistic Approach to Undesired Content Detection in the Real World. Proceedings of the AAAI Conference on Artificial Intelligence 37 12 (Jun. 2023) 15009\u201315018. 10.1609\/aaai.v37i12.26752https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/26752 https:\/\/github.com\/openai\/moderation-api-release.","DOI":"10.1609\/aaai.v37i12.26752"},{"key":"e_1_3_3_2_50_2","doi-asserted-by":"publisher","DOI":"10.1145\/3593013.3594109"},{"key":"e_1_3_3_2_51_2","doi-asserted-by":"publisher","unstructured":"Dana\u00eb Metaxa Michelle\u00a0A. Gan Su Goh Jeff Hancock and James\u00a0A. Landay. 2021. An Image of Society: Gender and Racial Representation and Impact in Image Search Results for Occupations. Proc. ACM Hum.-Comput. Interact. 5 CSCW1 Article 26 (April 2021) 23\u00a0pages. 10.1145\/3449100https:\/\/doi.org\/10.1145\/3449100.","DOI":"10.1145\/3449100"},{"key":"e_1_3_3_2_52_2","doi-asserted-by":"crossref","unstructured":"Dana\u00eb Metaxa Joon\u00a0Sung Park Ronald\u00a0E Robertson Karrie Karahalios Christo Wilson Jeff Hancock Christian Sandvig et\u00a0al. 2021. Auditing algorithms: Understanding algorithmic systems from the outside in. Foundations and Trends\u00ae in Human\u2013Computer Interaction 14 4 (2021) 272\u2013344.","DOI":"10.1561\/1100000083"},{"key":"e_1_3_3_2_53_2","unstructured":"Alan Mislove. 2023. Red-Teaming Large Language Models to Identify Novel AI Risks. https:\/\/bidenwhitehouse.archives.gov\/ostp\/news-updates\/2023\/08\/29\/red-teaming-large-language-models-to-identify-novel-ai-risks\/."},{"key":"e_1_3_3_2_54_2","doi-asserted-by":"publisher","DOI":"10.1145\/2872427.2883062"},{"key":"e_1_3_3_2_55_2","unstructured":"OctoAI. 2024. Using Llama Guard to moderate text. https:\/\/web.archive.org\/web\/20240622064550\/https:\/\/octo.ai\/docs\/text-gen-solution\/llama-guard."},{"key":"e_1_3_3_2_56_2","unstructured":"OpenAI. 2024. GPT-4 System Card. https:\/\/cdn.openai.com\/papers\/gpt-4-system-card.pdf."},{"key":"e_1_3_3_2_57_2","unstructured":"OpenAI. 2024. Terms of Use. https:\/\/openai.com\/policies\/row-terms-of-use\/."},{"key":"e_1_3_3_2_58_2","doi-asserted-by":"publisher","DOI":"10.1145\/3593013.3594078"},{"key":"e_1_3_3_2_59_2","unstructured":"Kate Payne. 2024. An AI chatbot pushed a teen to kill himself a lawsuit against its creator alleges."},{"key":"e_1_3_3_2_60_2","unstructured":"S Ray. 2023. OpenAI Sued For Defamation After ChatGPT Generates Fake Complaint Accusing Man Of Embezzlement. Forbes (2023)."},{"key":"e_1_3_3_2_61_2","doi-asserted-by":"publisher","DOI":"10.2307\/j.ctvhrcz0v"},{"key":"e_1_3_3_2_62_2","unstructured":"Alexander Robey Zachary Ravichandran Vijay Kumar Hamed Hassani and George\u00a0J Pappas. 2024. Jailbreaking llm-controlled robots. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2410.13691 (2024)."},{"key":"e_1_3_3_2_63_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1163"},{"key":"e_1_3_3_2_64_2","unstructured":"Ranjit Singh Borhane Blili-Hamelin Carol Anderson Emnet Tafesse Briana Vecchione Beth Duckles and Jacob Metcalf. 2025. Red-Teaming in the Public Interest. Data & Society Research Institute (2025)."},{"key":"e_1_3_3_2_65_2","unstructured":"Victor Storchan Ravin Kumar Rumman Chowdhury Seraphina Goldfarb-Tarrant and Sven Cattell. 2024. GENERATIVE AI RED TEAMING CHALLENGE: TRANSPARENCY REPORT. https:\/\/drive.google.com\/file\/d\/1JqpbIP6DNomkb32umLoiEPombK2-0Rc-\/view."},{"key":"e_1_3_3_2_66_2","unstructured":"TMDB. 2024. The Movie Database. https:\/\/www.themoviedb.org\/."},{"key":"e_1_3_3_2_67_2","doi-asserted-by":"crossref","unstructured":"Fabio Urbina Filippa Lentzos C\u00e9dric Invernizzi and Sean Ekins. 2022. Dual use of artificial-intelligence-powered drug discovery. Nature machine intelligence 4 3 (2022) 189\u2013191.","DOI":"10.1038\/s42256-022-00465-9"},{"key":"e_1_3_3_2_68_2","unstructured":"U.S. Code. 1998. Children\u2019s Online Privacy Protection Rule (\"COPPA\"). 15 U.S.C. 6501\u20136505 https:\/\/www.ftc.gov\/legal-library\/browse\/rules\/childrens-online-privacy-protection-rule-coppa."},{"key":"e_1_3_3_2_69_2","first-page":"1324","volume-title":"Proceedings of the 29th International Conference on Computational Linguistics","author":"Venkit Pranav\u00a0Narayanan","year":"2022","unstructured":"Pranav\u00a0Narayanan Venkit, Mukund Srinath, and Shomir Wilson. 2022. A study of implicit bias in pretrained language models against people with disabilities. In Proceedings of the 29th International Conference on Computational Linguistics. 1324\u20131332."},{"key":"e_1_3_3_2_70_2","unstructured":"Russell\u00a0T. Vought. 2025. Accelerating Federal Use of AI through Innovation Governance and Public Trust. Executive Office of the President Office of Management and Budget (2025)."},{"key":"e_1_3_3_2_71_2","unstructured":"Scott Wiener. 2024. SB 1047: Safe and Secure Innovation for Frontier Artificial Intelligence Models Act. California Senate Bill 1047 in the 2023-24 Legislative Session."},{"key":"e_1_3_3_2_72_2","doi-asserted-by":"publisher","DOI":"10.1145\/3630106.3658922"},{"key":"e_1_3_3_2_73_2","unstructured":"SD Young. 2024. Advancing governance innovation and risk management for agency use of artificial intelligence. Executive Office of the President Office of Management and Budget (2024)."},{"key":"e_1_3_3_2_74_2","doi-asserted-by":"crossref","unstructured":"Travis Zack Eric Lehman Mirac Suzgun Jorge\u00a0A Rodriguez Leo\u00a0Anthony Celi Judy Gichoya Dan Jurafsky Peter Szolovits David\u00a0W Bates Raja-Elie\u00a0E Abdulnour et\u00a0al. 2024. Assessing the potential of GPT-4 to perpetuate racial and gender biases in health care: a model evaluation study. The Lancet Digital Health 6 1 (2024) e12\u2013e22.","DOI":"10.1016\/S2589-7500(23)00225-X"},{"key":"e_1_3_3_2_75_2","volume-title":"International Conference on Learning Representations (ICLR)","author":"Zeng Yi","year":"2025","unstructured":"Yi Zeng, Yu Yang, Andy Zhou, Jeffrey\u00a0Ziwei Tan, Yuheng Tu, Yifan Mai, Kevin Klyman, Minzhou Pan, Ruoxi Jia, Dawn Song, et\u00a0al. 2025. AIR-BENCH 2024: A Safety Benchmark based on Regulation and Policies Specified Risk Categories. In International Conference on Learning Representations (ICLR)."}],"event":{"name":"EAAMO '25: Equity and Access in Algorithms, Mechanisms, and Optimization","location":"Pittsburgh USA","acronym":"EAAMO '25","sponsor":["SIGecom Special Interest Group on Economics and Computation","SIGAI ACM Special Interest Group on Artificial Intelligence"]},"container-title":["Proceedings of the 5th ACM Conference on Equity and Access in Algorithms, Mechanisms, and Optimization"],"original-title":[],"deposited":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T09:15:01Z","timestamp":1761815701000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3757887.3763010"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,4]]},"references-count":74,"alternative-id":["10.1145\/3757887.3763010","10.1145\/3757887"],"URL":"https:\/\/doi.org\/10.1145\/3757887.3763010","relation":{},"subject":[],"published":{"date-parts":[[2025,11,4]]},"assertion":[{"value":"2025-11-04","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}