{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T18:45:37Z","timestamp":1782758737112,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":129,"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":[{"name":"R3AI R10 Research Regroupment","award":["n\/a"],"award-info":[{"award-number":["n\/a"]}]},{"name":"Mila P2v5 grant","award":["n\/a"],"award-info":[{"award-number":["n\/a"]}]},{"name":"Mila-Samsung grant","award":["n\/a"],"award-info":[{"award-number":["n\/a"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,6,25]]},"DOI":"10.1145\/3805689.3806486","type":"proceedings-article","created":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T17:52:08Z","timestamp":1782755528000},"page":"4491-4510","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Societal Frameworks Can Improve LLM Alignment"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7326-9594","authenticated-orcid":false,"given":"Karolina","family":"Sta\u0144czak","sequence":"first","affiliation":[{"name":"ETH, Zurich, Switzerland, McGill University, Montr\u00e9al, QC, Canada, and Mila Quebec AI Institute, Montr\u00e9al, QC, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2161-2690","authenticated-orcid":false,"given":"Nicholas","family":"Meade","sequence":"additional","affiliation":[{"name":"McGill University, Montr\u00e9al, QC, Canada, and Mila Quebec AI Institute, Montr\u00e9al, QC, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7325-7064","authenticated-orcid":false,"given":"Mehar","family":"Bhatia","sequence":"additional","affiliation":[{"name":"McGill University, Montr\u00e9al, QC, Canada, and Mila Quebec AI Institute, Montr\u00e9al, QC, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-4502-3489","authenticated-orcid":false,"given":"Hattie","family":"Zhou","sequence":"additional","affiliation":[{"name":"McGill University, Montr\u00e9al, QC, Canada, and Mila Quebec AI Institute, Montr\u00e9al, QC, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9337-7506","authenticated-orcid":false,"given":"Konstantin","family":"B\u00f6ttinger","sequence":"additional","affiliation":[{"name":"Fraunhofer AISEC, Munich, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-5355-8059","authenticated-orcid":false,"given":"Jeremy","family":"Barnes","sequence":"additional","affiliation":[{"name":"ServiceNow, Montr\u00e9al, QC, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-5425-4834","authenticated-orcid":false,"given":"Jason","family":"Stanley","sequence":"additional","affiliation":[{"name":"ServiceNow, Montr\u00e9al, QC, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5078-7233","authenticated-orcid":false,"given":"Nicolas","family":"Papernot","sequence":"additional","affiliation":[{"name":"University of Toronto, Toronto, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0249-7607","authenticated-orcid":false,"given":"Nicolas","family":"Chapados","sequence":"additional","affiliation":[{"name":"ServiceNow, Montr\u00e9al, QC, Canada, and Mila Quebec AI Institute, Montr\u00e9al, QC, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7545-909X","authenticated-orcid":false,"given":"Denis","family":"Therien","sequence":"additional","affiliation":[{"name":"McGill University, Montr\u00e9al, QC, Canada, and ServiceNow, Montr\u00e9al, QC, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8918-486X","authenticated-orcid":false,"given":"Timothy P","family":"Lillicrap","sequence":"additional","affiliation":[{"name":"Google Deepmind, London, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-2502-9262","authenticated-orcid":false,"given":"Ana","family":"Marasovi\u0107","sequence":"additional","affiliation":[{"name":"University of Utah, Salt Lake City, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8517-7782","authenticated-orcid":false,"given":"Sylvie","family":"Delacroix","sequence":"additional","affiliation":[{"name":"King's College London, London, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4124-8187","authenticated-orcid":false,"given":"Gillian K","family":"Hadfield","sequence":"additional","affiliation":[{"name":"Johns Hopkins University, Baltimore, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3753-0323","authenticated-orcid":false,"given":"Siva","family":"Reddy","sequence":"additional","affiliation":[{"name":"McGill University, Montr\u00e9al, Canada, Mila Quebec AI Institute, Montr\u00e9al, Canada, and ServiceNow, Montr\u00e9al, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,6,25]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.671"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1257\/jep.25.2.181"},{"key":"e_1_3_2_1_3_1","first-page":"e35179","article-title":"Artificial Hallucinations in ChatGPT","volume":"15","author":"Alkaissi Hussam","year":"2023","unstructured":"Hussam Alkaissi and Samy I McFarlane. 2023. Artificial Hallucinations in ChatGPT: Implications in Scientific Writing. Cureus 15 (2023), e35179. https:\/\/pmc.ncbi.nlm.nih.gov\/articles\/PMC9939079\/","journal-title":"Implications in Scientific Writing. Cureus"},{"key":"e_1_3_2_1_4_1","unstructured":"Dario Amodei Chris Olah Jacob Steinhardt Paul Christiano John Schulman and Dan Man\u00e9. 2016. Concrete Problems in AI Safety. arXiv:1606.06565 [cs.AI] https:\/\/arxiv.org\/abs\/1606.06565"},{"key":"e_1_3_2_1_5_1","unstructured":"Anthropic. 2023. Claude's Constitution. https:\/\/www.anthropic.com\/index\/claudes-constitution. Accessed: 2025-01-27."},{"key":"e_1_3_2_1_6_1","unstructured":"Anthropic. 2023. Collective Constitutional AI: Aligning a Language Model with Public Input. https:\/\/www.anthropic.com\/index\/collective-constitutional-ai-aligning-a-language-model-with-public-input. Accessed: 2025-01-27."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1147\/JRD.2019.2942288"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1525\/9780520411586-038"},{"key":"e_1_3_2_1_9_1","unstructured":"Amanda Askell Yuntao Bai Anna Chen Dawn Drain Deep Ganguli Tom Henighan Andy Jones Nicholas Joseph Ben Mann Nova DasSarma Nelson Elhage Zac Hatfield-Dodds Danny Hernandez Jackson Kernion Kamal Ndousse Catherine Olsson Dario Amodei Tom Brown Jack Clark Sam McCandlish Chris Olah and Jared Kaplan. 2021. A General Language Assistant as a Laboratory for Alignment. arXiv:2112.00861 [cs.CL] https:\/\/arxiv.org\/abs\/2112.00861"},{"key":"e_1_3_2_1_10_1","volume-title":"Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback. ArXiv abs\/2204.05862","author":"Bai Yuntao","year":"2022","unstructured":"Yuntao Bai, Andy Jones, Kamal Ndousse, Amanda Askell, Anna Chen, Nova Dassarma, Dawn Drain, Stanislav Fort, Deep Ganguli, Tom Henighan, Nicholas Joseph, Saurav Kadavath, John Kernion, Tom Conerly, Sheer El-Showk, Nelson Elhage, Zac Hatfield-Dodds, Danny Hernandez, Tristan Hume, Scott Johnston, Shauna Kravec, Liane Lovitt, Neel Nanda, Catherine Olsson, Dario Amodei, Tom B. Brown, Jack Clark, Sam McCandlish, Christopher Olah, Benjamin Mann, and Jared Kaplan. 2022. Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback. ArXiv abs\/2204.05862 (2022). https:\/\/arxiv.org\/abs\/2204.05862"},{"key":"e_1_3_2_1_11_1","unstructured":"Yuntao Bai Saurav Kadavath Sandipan Kundu Amanda Askell Jackson Kernion Andy Jones Anna Chen Anna Goldie Azalia Mirhoseini Cameron McKinnon Carol Chen Catherine Olsson Christopher Olah Danny Hernandez Dawn Drain Deep Ganguli Dustin Li Eli Tran-Johnson Ethan Perez Jamie Kerr Jared Mueller Jeffrey Ladish Joshua Landau Kamal Ndousse Kamile Lukosuite Liane Lovitt Michael Sellitto Nelson Elhage Nicholas Schiefer Noemi Mercado Nova DasSarma Robert Lasenby Robin Larson Sam Ringer Scott Johnston Shauna Kravec Sheer El Showk Stanislav Fort Tamera Lanham Timothy Telleen-Lawton Tom Conerly Tom Henighan Tristan Hume Samuel R. Bowman Zac Hatfield-Dodds Ben Mann Dario Amodei Nicholas Joseph Sam McCandlish Tom Brown and Jared Kaplan. 2022. Constitutional AI: Harmlessness from AI Feedback. arXiv:2212.08073 [cs.CL] https:\/\/arxiv.org\/abs\/2212.08073"},{"key":"e_1_3_2_1_12_1","volume-title":"Proceedings of The 1st Conference on Lifelong Learning Agents (Proceedings of Machine Learning Research","volume":"660","author":"Benavides-Prado Diana","year":"2022","unstructured":"Diana Benavides-Prado and Patricia Riddle. 2022. A Theory for Knowledge Transfer in Continual Learning. In Proceedings of The 1st Conference on Lifelong Learning Agents (Proceedings of Machine Learning Research, Vol. 199), Sarath Chandar, Razvan Pascanu, and Doina Precup (Eds.). PMLR, Montr\u00e9al, Canada, 647\u2013660. https:\/\/proceedings.mlr.press\/v199\/prado22a.html"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00041"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-024-56648-4"},{"key":"e_1_3_2_1_15_1","volume-title":"Value Drifts: Tracing Value Alignment During LLM Post-Training. arXiv:2510.26707 [cs.CL] https:\/\/arxiv.org\/abs\/2510.26707","author":"Bhatia Mehar","year":"2025","unstructured":"Mehar Bhatia, Shravan Nayak, Gaurav Kamath, Marius Mosbach, Karolina Sta\u0144czak, Vered Shwartz, and Siva Reddy. 2025. Value Drifts: Tracing Value Alignment During LLM Post-Training. arXiv:2510.26707 [cs.CL] https:\/\/arxiv.org\/abs\/2510.26707"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3461702.3462571"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1093\/acprof:oso\/9780190622046.001.0001"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11023-021-09584-5"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"crossref","unstructured":"John D. Black Nigar Hashimzade and Gareth Myles (Eds.). 2017. A Dictionary of Economics (5th ed.). Oxford University Press Oxford. 459 pages. https:\/\/books.google.ca\/books?id=WyvYDQAAQBAJ&pg=PT459&redir_esc=y#v=onepage&q&f=false","DOI":"10.1093\/acref\/9780198759430.001.0001"},{"key":"e_1_3_2_1_20_1","unstructured":"Ryan Boldi Li Ding Lee Spector and Scott Niekum. 2024. Pareto-Optimal Learning from Preferences with Hidden Context. arXiv:2406.15599 [cs.LG] https:\/\/arxiv.org\/abs\/2406.15599"},{"key":"e_1_3_2_1_21_1","volume-title":"Contract Theory","author":"Bolton Patrick","year":"2025","unstructured":"Patrick Bolton and Mathias Dewatripont. 2005. Contract Theory. MIT Press Books, Vol. 1. The MIT Press. https:\/\/ideas.repec.org\/b\/mtp\/titles\/0262025760.html"},{"key":"e_1_3_2_1_22_1","first-page":"324","article-title":"Rank Analysis of Incomplete Block Designs","volume":"39","author":"Bradley Ralph Allan","year":"1952","unstructured":"Ralph Allan Bradley and Milton E. Terry. 1952. Rank Analysis of Incomplete Block Designs: I. The Method of Paired Comparisons. Biometrika 39, 3\/4 (1952), 324\u2013345. http:\/\/www.jstor.org\/stable\/2334029","journal-title":"I. The Method of Paired Comparisons. Biometrika"},{"key":"e_1_3_2_1_23_1","volume-title":"Computational Aspects of Cooperative Game Theory (Synthesis Lectures on Artificial Inetlligence and Machine Learning)","author":"Chalkiadakis Georgios","unstructured":"Georgios Chalkiadakis, Edith Elkind, and Michael Wooldridge. 2011. Computational Aspects of Cooperative Game Theory (Synthesis Lectures on Artificial Inetlligence and Machine Learning) (1st ed.). Morgan & Claypool Publishers. https:\/\/link.springer.com\/book\/10.1007\/978-3-031-01558-8","edition":"1"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"crossref","unstructured":"Patrick Chao Alexander Robey Edgar Dobriban Hamed Hassani George J. Pappas and Eric Wong. 2024. Jailbreaking Black Box Large Language Models in Twenty Queries. arXiv:2310.08419 [cs.LG] https:\/\/arxiv.org\/abs\/2310.08419","DOI":"10.1109\/SaTML64287.2025.00010"},{"key":"e_1_3_2_1_25_1","volume-title":"Shuyue Stella Li, Mehar Bhatia, Sahithya Ravi, Yulia Tsvetkov, Vered Shwartz, and Yejin Choi.","author":"Chiu Yu Ying","year":"2024","unstructured":"Yu Ying Chiu, Liwei Jiang, Maria Antoniak, Chan Young Park, Shuyue Stella Li, Mehar Bhatia, Sahithya Ravi, Yulia Tsvetkov, Vered Shwartz, and Yejin Choi. 2024. CulturalTeaming: AI-Assisted Interactive Red-Teaming for Challenging LLMs'(Lack of) Multicultural Knowledge. arXiv preprint arXiv:2404.06664 (2024). https:\/\/arxiv.org\/abs\/2404.06664"},{"key":"e_1_3_2_1_26_1","volume-title":"Garnett (Eds.)","volume":"30","author":"Christiano Paul F","year":"2017","unstructured":"Paul F Christiano, Jan Leike, Tom Brown, Miljan Martic, Shane Legg, and Dario Amodei. 2017. Deep Reinforcement Learning from Human Preferences. 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\/d5e2c0adad503c91f91df240d0cd4e49-Paper.pdf"},{"key":"e_1_3_2_1_27_1","volume-title":"Zwicker","author":"Conitzer Vincent","year":"2024","unstructured":"Vincent Conitzer, Rachel Freedman, Jobst Heitzig, Wesley H. Holliday, Bob M. Jacobs, Nathan Lambert, Milan Mosse, Eric Pacuit, Stuart Russell, Hailey Schoelkopf, Emanuel Tewolde, and William S. Zwicker. 2024. Position: Social Choice Should Guide AI Alignment in Dealing with Diverse Human Feedback. In Proceedings of the 41st International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 235), Ruslan Salakhutdinov, Zico Kolter, Katherine Heller, Adrian Weller, Nuria Oliver, Jonathan Scarlett, and Felix Berkenkamp (Eds.). PMLR, 9346\u20139360. https:\/\/proceedings.mlr.press\/v235\/conitzer24a.html"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","unstructured":"A. Feder Cooper Christopher A. Choquette-Choo Miranda Bogen Matthew Jagielski Katja Filippova Ken Liu Alexandra Chouldechova Jamie Hayes Yangsibo Huang Niloofar Mireshghallah Ilia Shumailov Eleni Triantafillou Peter Kairouz Nicole Mitchell Percy Liang Daniel E. Ho Yejin Choi Sanmi Koyejo Fernando Delgado James Grimmelmann Vitaly Shmatikov Christopher De Sa Solon Barocas Amy Cyphert Mark A. Lemley Danah Boyd Jennifer Wortman Vaughan Miles Brundage David Bau Seth Neel Abigail Jacobs Andreas Terzis Hanna Wallach Nicolas Papernot and Katherine Lee. 2024. Machine Unlearning Doesn't Do What You Think: Lessons for Generative AI Policy Research and Practice. SSRN (December 2024). doi:10.2139\/ssrn.5060253","DOI":"10.2139\/ssrn.5060253"},{"key":"e_1_3_2_1_29_1","first-page":"1124","article-title":"On Welfare-Centric Fair Reinforcement Learning","volume":"3","author":"Cousins Cyrus","year":"2024","unstructured":"Cyrus Cousins, Kavosh Asadi, Elita Lobo, and Michael Littman. 2024. On Welfare-Centric Fair Reinforcement Learning. Reinforcement Learning Journal 3 (2024), 1124\u20131137. https:\/\/rlj.cs.umass.edu\/2024\/papers\/Paper133.html","journal-title":"Reinforcement Learning Journal"},{"key":"e_1_3_2_1_30_1","article-title":"Underspecification presents challenges for credibility in modern machine learning","volume":"23","author":"D'Amour Alexander","year":"2022","unstructured":"Alexander D'Amour, Katherine Heller, Dan Moldovan, Ben Adlam, Babak Alipanahi, Alex Beutel, Christina Chen, Jonathan Deaton, Jacob Eisenstein, Matthew D. Hoffman, Farhad Hormozdiari, Neil Houlsby, Shaobo Hou, Ghassen Jerfel, Alan Karthikesalingam, Mario Lucic, Yian Ma, Cory McLean, Diana Mincu, Akinori Mitani, Andrea Montanari, Zachary Nado, Vivek Natarajan, Christopher Nielson, Thomas F. Osborne, Rajiv Raman, Kim Ramasamy, Rory Sayres, Jessica Schrouff, Martin Seneviratne, Shannon Sequeira, Harini Suresh, Victor Veitch, Max Vladymyrov, Xuezhi Wang, Kellie Webster, Steve Yadlowsky, Taedong Yun, Xiaohua Zhai, and D. Sculley. 2022. Underspecification presents challenges for credibility in modern machine learning. Journal of Machine Learning Research 23, 1, Article 226 (Jan. 2022), 61 pages. https:\/\/dl.acm.org\/doi\/pdf\/10.5555\/3586589.3586815","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1016\/S1574-0110(02)80014-5"},{"key":"e_1_3_2_1_32_1","volume-title":"Lost in Conversation? Hermeneutics, uncertainty and large language models. SSRN (April 21","author":"Delacroix Sylvie","year":"2024","unstructured":"Sylvie Delacroix. 2024. Lost in Conversation? Hermeneutics, uncertainty and large language models. SSRN (April 21 2024). https:\/\/ssrn.com\/abstract=4751774"},{"key":"e_1_3_2_1_33_1","volume-title":"Proceedings of the 8th ACM\/IEEE International Conference on Human-Robot Interaction","author":"Dragan Anca D.","unstructured":"Anca D. Dragan, Kenton C.T. Lee, and Siddhartha S. Srinivasa. 2013. Legibility and predictability of robot motion. In Proceedings of the 8th ACM\/IEEE International Conference on Human-Robot Interaction (Tokyo, Japan) (HRI '13). IEEE Press, 301\u2013308. https:\/\/ieeexplore.ieee.org\/document\/6483603"},{"key":"e_1_3_2_1_34_1","volume-title":"Towards Measuring the Representation of Subjective Global Opinions in Language Models. In First Conference on Language Modeling. https:\/\/openreview.net\/forum?id=zl16jLb91v","author":"Durmus Esin","year":"2024","unstructured":"Esin Durmus, Karina Nguyen, Thomas Liao, Nicholas Schiefer, Amanda Askell, Anton Bakhtin, Carol Chen, Zac Hatfield-Dodds, Danny Hernandez, Nicholas Joseph, Liane Lovitt, Sam McCandlish, Orowa Sikder, Alex Tamkin, Janel Thamkul, Jared Kaplan, Jack Clark, and Deep Ganguli. 2024. Towards Measuring the Representation of Subjective Global Opinions in Language Models. In First Conference on Language Modeling. https:\/\/openreview.net\/forum?id=zl16jLb91v"},{"key":"e_1_3_2_1_35_1","unstructured":"F. Echenique N. Immorlica V.V. Vazirani and A.E. Roth. 2023. Contract Theory. Cambridge University Press 614\u2013624. https:\/\/books.google.ca\/books?id=1ea-EAAAQBAJ"},{"key":"e_1_3_2_1_36_1","unstructured":"Joe Edelman Tan Zhi-Xuan Ryan Lowe Oliver Klingefjord Vincent Wang-Mascianica Matija Franklin Ryan Othniel Kearns Ellie Hain Atrisha Sarkar Michiel Bakker Fazl Barez David Duvenaud Jakob Foerster Iason Gabriel Joseph Gubbels Bryce Goodman Andreas Haupt Jobst Heitzig Julian Jara-Ettinger Atoosa Kasirzadeh James Ravi Kirkpatrick Andrew Koh W. Bradley Knox Philipp Koralus Joel Lehman Sydney Levine Samuele Marro Manon Revel Toby Shorin Morgan Sutherland Michael Henry Tessler Ivan Vendrov and James Wilken-Smith. 2025. Full-Stack Alignment: Co-Aligning AI and Institutions with Thick Models of Value. (2025). arXiv:2512.03399 [cs.LG] https:\/\/arxiv.org\/abs\/2512.03399"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.2307\/258191"},{"key":"e_1_3_2_1_38_1","volume-title":"Lipton","author":"Feffer Michael","year":"2023","unstructured":"Michael Feffer, Hoda Heidari, and Zachary C. Lipton. 2023. Moral Machine or Tyranny of the Majority? arXiv:2305.17319 [cs.CY] https:\/\/arxiv.org\/abs\/2305.17319"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1215\/08992363-10742593"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11023-020-09539-2"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11098-025-02300-4"},{"key":"e_1_3_2_1_42_1","unstructured":"Iason Gabriel Arianna Manzini Geoff Keeling Lisa Anne Hendricks Verena Rieser Hasan Iqbal Nenad Toma\u0161ev Ira Ktena Zachary Kenton Mikel Rodriguez Seliem El-Sayed Sasha Brown Canfer Akbulut Andrew Trask Edward Hughes A. Stevie Bergman Renee Shelby Nahema Marchal Conor Griffin Juan Mateos-Garcia Laura Weidinger Winnie Street Benjamin Lange Alex Ingerman Alison Lentz Reed Enger Andrew Barakat Victoria Krakovna John Oliver Siy Zeb Kurth-Nelson Amanda McCroskery Vijay Bolina Harry Law Murray Shanahan Lize Alberts Borja Balle Sarah de Haas Yetunde Ibitoye Allan Dafoe Beth Goldberg S\u00e9bastien Krier Alexander Reese Sims Witherspoon Will Hawkins Maribeth Rauh Don Wallace Matija Franklin Josh A. Goldstein Joel Lehman Michael Klenk Shannon Vallor Courtney Biles Meredith Ringel Morris Helen King Blaise Ag\u00fcera y Arcas William Isaac and James Manyika. 2024. The Ethics of Advanced AI Assistants. (2024). arXiv:2404.16244 [cs.CY] https:\/\/arxiv.org\/abs\/2404.16244"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1001\/archinternmed.2009.481"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1086\/261967"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3458723"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-psych-033020-013319"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1111\/1468-2230.12352"},{"key":"e_1_3_2_1_48_1","unstructured":"Ryan Greenblatt Carson Denison Benjamin Wright Fabien Roger Monte MacDiarmid Sam Marks Johannes Treutlein Tim Belonax Jack Chen David Duvenaud Akbir Khan Julian Michael S\u00f6ren Mindermann Ethan Perez Linda Petrini Jonathan Uesato Jared Kaplan Buck Shlegeris Samuel R. Bowman and Evan Hubinger. 2024. Alignment faking in large language models. arXiv:2412.14093 [cs.AI] https:\/\/arxiv.org\/abs\/2412.14093"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/3306618.3314258"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3306618.3314250"},{"key":"e_1_3_2_1_51_1","volume-title":"Garnett (Eds.)","volume":"30","author":"Hadfield-Menell Dylan","year":"2017","unstructured":"Dylan Hadfield-Menell, Smitha Milli, Pieter Abbeel, Stuart J Russell, and Anca Dragan. 2017. Inverse Reward Design. 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\/32fdab6559cdfa4f167f8c31b9199643-Paper.pdf"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1016\/B0-08-043076-7\/00586-6"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyg.2018.00849"},{"key":"e_1_3_2_1_54_1","volume-title":"Fundamental Problems With Model Editing: How Should Rational Belief Revision Work in LLMs? Transactions on Machine Learning Research","author":"Hase Peter","year":"2024","unstructured":"Peter Hase, Thomas Hofweber, Xiang Zhou, Elias Stengel-Eskin, and Mohit Bansal. 2024. Fundamental Problems With Model Editing: How Should Rational Belief Revision Work in LLMs? Transactions on Machine Learning Research (2024). https:\/\/openreview.net\/forum?id=LRf19n5Ly3"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.482"},{"key":"e_1_3_2_1_56_1","unstructured":"Saffron Huang Esin Durmus Miles McCain Kunal Handa Alex Tamkin Jerry Hong Michael Stern Arushi Somani Xiuruo Zhang and Deep Ganguli. 2025. Values in the Wild: Discovering and Analyzing Values in Real-World Language Model Interactions. (2025). arXiv:2504.15236 [cs.CL] https:\/\/arxiv.org\/abs\/2504.15236"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2018.2864889"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.4230\/LIPIcs.FORC.2020.2"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.23915\/distill.00021"},{"key":"e_1_3_2_1_60_1","unstructured":"Geoffrey Irving Paul Christiano and Dario Amodei. 2018. AI safety via debate. arXiv:1805.00899 [stat.ML] https:\/\/arxiv.org\/abs\/1805.00899"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1145\/3442188.3445923"},{"key":"e_1_3_2_1_62_1","unstructured":"Daniel Kahneman. 2011. Thinking Fast and Slow. Allen Lane. https:\/\/books.google.ca\/books?id=AV9x8XakdV0C"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1086\/649046"},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1609\/hcomp.v8i1.7465"},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.techsoc.2020.101378"},{"key":"e_1_3_2_1_66_1","volume-title":"Katerina Margatina, Rafael Mosquera, Juan Manuel Ciro, Max Bartolo, Adina Williams, He He, Bertie Vidgen, and Scott A. Hale.","author":"Kirk Hannah Rose","year":"2024","unstructured":"Hannah Rose Kirk, Alexander Whitefield, Paul R\u00f6ttger, Andrew Michael Bean, Katerina Margatina, Rafael Mosquera, Juan Manuel Ciro, Max Bartolo, Adina Williams, He He, Bertie Vidgen, and Scott A. Hale. 2024. The PRISM Alignment Dataset: What Participatory, Representative and Individualised Human Feedback Reveals About the Subjective and Multicultural Alignment of Large Language Models. In The Thirty-eight Conference on Neural Information Processing Systems Datasets and Benchmarks Track. https:\/\/openreview.net\/forum?id=DFr5hteojx"},{"key":"e_1_3_2_1_67_1","unstructured":"Oliver Klingefjord Ryan Lowe and Joe Edelman. 2024. What are human values and how do we align AI to them? arXiv:2404.10636 [cs.CY] https:\/\/arxiv.org\/abs\/2404.10636"},{"key":"e_1_3_2_1_68_1","unstructured":"Cody Kommers Drew Hemment Maria Antoniak Joel Z. Leibo Hoyt Long Emily Robinson and Adam Sobey. 2025. Meaning Is Not A Metric: Using LLMs to make cultural context legible at scale. (2025). arXiv:2505.23785 [cs.CL] https:\/\/arxiv.org\/abs\/2505.23785"},{"key":"e_1_3_2_1_69_1","volume-title":"Proceedings of the 19th International Conference on Autonomous Agents and MultiAgent Systems","author":"K\u00f6ster Raphael","year":"1887","unstructured":"Raphael K\u00f6ster, Dylan Hadfield-Menell, Gillian K. Hadfield, and Joel Z. Leibo. 2020. Silly Rules Improve the Capacity of Agents to Learn Stable Enforcement and Compliance Behaviors. In Proceedings of the 19th International Conference on Autonomous Agents and MultiAgent Systems (Auckland, New Zealand) (AAMAS '20). International Foundation for Autonomous Agents and Multiagent Systems, Richland, SC, 1887\u20131888. https:\/\/dl.acm.org\/doi\/10.5555\/3398761.3399016"},{"key":"e_1_3_2_1_70_1","unstructured":"Jan Leike David Krueger Tom Everitt Miljan Martic Vishal Maini and Shane Legg. 2018. Scalable agent alignment via reward modeling: A research direction. arXiv:1811.07871 [cs.LG] https:\/\/arxiv.org\/abs\/1811.07871"},{"key":"e_1_3_2_1_71_1","doi-asserted-by":"publisher","DOI":"10.1098\/rstb.2013.0302"},{"key":"e_1_3_2_1_72_1","doi-asserted-by":"publisher","DOI":"10.1609\/aies.v7i1.31686"},{"key":"e_1_3_2_1_73_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.818"},{"key":"e_1_3_2_1_74_1","volume-title":"Muhammad Faaiz Taufiq, and Hang Li","author":"Liu Yang","year":"2024","unstructured":"Yang Liu, Yuanshun Yao, Jean-Francois Ton, Xiaoying Zhang, Ruocheng Guo, Hao Cheng, Yegor Klochkov, Muhammad Faaiz Taufiq, and Hang Li. 2024. Trustworthy LLMs: A Survey and Guideline for Evaluating Large Language Models' Alignment. arXiv:2308.05374 [cs.AI] https:\/\/arxiv.org\/abs\/2308.05374"},{"key":"e_1_3_2_1_75_1","first-page":"854","article-title":"Contracts: Adjustment of long-term economic relations under classical, neoclassical, and relational contract law","volume":"72","author":"Macneil Ian R","year":"1977","unstructured":"Ian R Macneil. 1977. Contracts: Adjustment of long-term economic relations under classical, neoclassical, and relational contract law. Northwestern University Law Review 72 (1977), 854. https:\/\/heinonline.org\/HOL\/LandingPage?handle=hein.journals\/illlr72&div=46&id=&page=","journal-title":"Northwestern University Law Review"},{"key":"e_1_3_2_1_76_1","doi-asserted-by":"publisher","DOI":"10.1145\/3313831.3376445"},{"key":"e_1_3_2_1_77_1","doi-asserted-by":"publisher","DOI":"10.1111\/1467-937X.00079"},{"key":"e_1_3_2_1_78_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-6494.2007.00476.x"},{"key":"e_1_3_2_1_79_1","volume-title":"The Enigma of Reason","author":"Mercier Hugo","unstructured":"Hugo Mercier and Dan Sperber. 2017. The Enigma of Reason. Harvard University Press. http:\/\/www.jstor.org\/stable\/j.ctv2sp3dd8"},{"key":"e_1_3_2_1_80_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11098-025-02347-3"},{"key":"e_1_3_2_1_81_1","volume-title":"Proceedings of the 39th International Conference on Machine Learning (Proceedings of Machine Learning Research","volume":"15831","author":"Mitchell Eric","year":"2022","unstructured":"Eric Mitchell, Charles Lin, Antoine Bosselut, Christopher D Manning, and Chelsea Finn. 2022. Memory-Based Model Editing at Scale. In Proceedings of the 39th International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 162), Kamalika Chaudhuri, Stefanie Jegelka, Le Song, Csaba Szepesvari, Gang Niu, and Sivan Sabato (Eds.). PMLR, 15817\u201315831. https:\/\/proceedings.mlr.press\/v162\/mitchell22a.html"},{"key":"e_1_3_2_1_82_1","doi-asserted-by":"publisher","DOI":"10.1145\/3287560.3287596"},{"key":"e_1_3_2_1_83_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11023-021-09568-5"},{"key":"e_1_3_2_1_84_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1817095116"},{"key":"e_1_3_2_1_85_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.329"},{"key":"e_1_3_2_1_86_1","unstructured":"Alondra Nelson. 2023. Thick Alignment. Keynote Talk at the 2023 ACM Conference on Fairness Accountability and Transparency (FAccT '23). https:\/\/www.youtube.com\/watch?v=Sq_XwqVTqvQ Accessed on 2026-01-13."},{"key":"e_1_3_2_1_87_1","volume-title":"The logic of collective action: public goods and the theory of groups. Number 124 in Harvard economic studies","author":"Olson Mancur","unstructured":"Mancur Olson. 1965. The logic of collective action: public goods and the theory of groups. Number 124 in Harvard economic studies. Harvard Univ. Press, Cambridge, Mass. 176 pages. https:\/\/www.hup.harvard.edu\/catalog.php?isbn=9780674537514"},{"key":"e_1_3_2_1_88_1","unstructured":"OpenAI. 2016. Faulty Reward Functions in the Wild. https:\/\/openai.com\/index\/faulty-reward-functions\/. Accessed: 2025-01-10."},{"key":"e_1_3_2_1_89_1","volume-title":"Oh (Eds.)","volume":"35","author":"Ouyang Long","year":"2022","unstructured":"Long Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida, Carroll Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, John Schulman, Jacob Hilton, Fraser Kelton, Luke Miller, Maddie Simens, Amanda Askell, Peter Welinder, Paul F Christiano, Jan Leike, and Ryan Lowe. 2022. Training language models to follow instructions with human feedback. In Advances in Neural Information Processing Systems, S. Koyejo, S. Mohamed, A. Agarwal, D. Belgrave, K. Cho, and A. Oh (Eds.), Vol. 35. Curran Associates, Inc., 27730\u201327744. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2022\/file\/b1efde53be364a73914f58805a001731-Paper-Conference.pdf"},{"key":"e_1_3_2_1_90_1","volume-title":"Learning Social Welfare Functions. In The Thirty-eighth Annual Conference on Neural Information Processing Systems. https:\/\/openreview.net\/forum?id=7O6KtaAr8n","author":"Pardeshi Kanad Shrikar","year":"2024","unstructured":"Kanad Shrikar Pardeshi, Itai Shapira, Ariel D. Procaccia, and Aarti Singh. 2024. Learning Social Welfare Functions. In The Thirty-eighth Annual Conference on Neural Information Processing Systems. https:\/\/openreview.net\/forum?id=7O6KtaAr8n"},{"key":"e_1_3_2_1_91_1","unstructured":"Joelle Pineau. 2020. The Machine Learning Reproducibility Checklist. https:\/\/www.cs.mcgill.ca\/~jpineau\/ReproducibilityChecklist.pdf Accessed: 2025-02-18."},{"key":"e_1_3_2_1_92_1","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2338"},{"key":"e_1_3_2_1_93_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.892"},{"key":"e_1_3_2_1_94_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.lindif.2007.03.011"},{"key":"e_1_3_2_1_95_1","volume-title":"Kristen Brent Venable, and Toby Walsh","author":"Rossi Francesca","year":"2011","unstructured":"Francesca Rossi, Kristen Brent Venable, and Toby Walsh. 2011. A Short Introduction to Preferences: Between AI and Social Choice (1st ed.). Morgan & Claypool Publishers. https:\/\/dl.acm.org\/doi\/10.5555\/2049991"},{"key":"e_1_3_2_1_96_1","volume-title":"NeurIPS 2023 Workshop on Instruction Tuning and Instruction Following. https:\/\/openreview.net\/forum?id=magEgFpK1y","author":"Saito Keita","year":"2023","unstructured":"Keita Saito, Akifumi Wachi, Koki Wataoka, and Youhei Akimoto. 2023. Verbosity Bias in Preference Labeling by Large Language Models. In NeurIPS 2023 Workshop on Instruction Tuning and Instruction Following. https:\/\/openreview.net\/forum?id=magEgFpK1y"},{"key":"e_1_3_2_1_97_1","unstructured":"John Schulman Filip Wolski Prafulla Dhariwal Alec Radford and Oleg Klimov. 2017. Proximal Policy Optimization Algorithms. arXiv:1707.06347 [cs.LG] https:\/\/arxiv.org\/abs\/1707.06347"},{"key":"e_1_3_2_1_98_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-94-010-1340-6_3"},{"key":"e_1_3_2_1_99_1","doi-asserted-by":"publisher","DOI":"10.1177\/0956797615586188"},{"key":"e_1_3_2_1_100_1","doi-asserted-by":"publisher","DOI":"10.2307\/1064452"},{"key":"e_1_3_2_1_101_1","article-title":"Uncertainty and Contract Law","volume":"46","author":"Seita Alex Y.","year":"1984","unstructured":"Alex Y. Seita. 1984. Uncertainty and Contract Law. University of Pittsburgh Law Review 46, 75 (1984). https:\/\/ssrn.com\/abstract=1692858","journal-title":"University of Pittsburgh Law Review"},{"key":"e_1_3_2_1_102_1","article-title":"Social Choice and Justice: A Review Article","author":"Sen Amartya","year":"1985","unstructured":"Amartya Sen. 1985. Social Choice and Justice: A Review Article. Journal of Economic Literature 23, December (1985). https:\/\/scholar.harvard.edu\/sen\/publications\/social-choice-and-justice-review-article Review article on K.J. Arrow's Collected Papers: Social Choice and Justice.","journal-title":"Journal of Economic Literature 23"},{"key":"e_1_3_2_1_103_1","doi-asserted-by":"publisher","DOI":"10.2307\/3003374"},{"key":"e_1_3_2_1_104_1","unstructured":"Tianhao Shen Renren Jin Yufei Huang Chuang Liu Weilong Dong Zishan Guo Xinwei Wu Yan Liu and Deyi Xiong. 2023. Large Language Model Alignment: A Survey. arXiv:2309.15025 [cs.CL] https:\/\/arxiv.org\/abs\/2309.15025"},{"key":"e_1_3_2_1_105_1","unstructured":"Ola Shorinwa Zhiting Mei Justin Lidard Allen Z. Ren and Anirudha Majumdar. 2024. A Survey on Uncertainty Quantification of Large Language Models: Taxonomy Open Research Challenges and Future Directions. arXiv:2412.05563 [cs.CL] https:\/\/arxiv.org\/abs\/2412.05563"},{"key":"e_1_3_2_1_106_1","volume-title":"Proceedings of the 36th International Conference on Neural Information Processing Systems","author":"Skalse Joar","year":"2024","unstructured":"Joar Skalse, Nikolaus H. R. Howe, Dmitrii Krasheninnikov, and David Krueger. 2024. Defining and characterizing reward hacking. In Proceedings of the 36th International Conference on Neural Information Processing Systems (New Orleans, LA, USA) (NIPS '22). Curran Associates Inc., Red Hook, NY, USA, Article 687, 12 pages. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2022\/hash\/3d719fee332caa23d5038b8a90e81796-Abstract-Conference.html"},{"key":"e_1_3_2_1_107_1","doi-asserted-by":"publisher","DOI":"10.5555\/3540261.3540709"},{"key":"e_1_3_2_1_108_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.emnlp-main.106"},{"key":"e_1_3_2_1_109_1","volume-title":"Proceedings of the 41st International Conference on Machine Learning. https:\/\/openreview.net\/forum?id=gQpBnRHwxM","author":"Sorensen Taylor","year":"2024","unstructured":"Taylor Sorensen, Jared Moore, Jillian Fisher, Mitchell L. Gordon, Niloofar Mireshghallah, Christopher Michael Rytting, Andre Ye, Liwei Jiang, Ximing Lu, Nouha Dziri, Tim Althoff, and Yejin Choi. 2024. Position: A Roadmap to Pluralistic Alignment. In Proceedings of the 41st International Conference on Machine Learning. https:\/\/openreview.net\/forum?id=gQpBnRHwxM"},{"key":"e_1_3_2_1_110_1","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3495977"},{"key":"e_1_3_2_1_111_1","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0115"},{"key":"e_1_3_2_1_112_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11098-024-02249-w"},{"key":"e_1_3_2_1_113_1","unstructured":"Kumar Tanmay Aditi Khandelwal Utkarsh Agarwal and Monojit Choudhury. 2023. Probing the Moral Development of Large Language Models through Defining Issues Test. arXiv:2309.13356 [cs.CL] https:\/\/arxiv.org\/abs\/2309.13356"},{"key":"e_1_3_2_1_114_1","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.4896078"},{"key":"e_1_3_2_1_115_1","doi-asserted-by":"publisher","DOI":"10.1111\/1468-0262.00052"},{"key":"e_1_3_2_1_116_1","volume-title":"Wortman Vaughan (Eds.)","volume":"34","author":"Turner Alex","year":"2021","unstructured":"Alex Turner, Logan Smith, Rohin Shah, Andrew Critch, and Prasad Tadepalli. 2021. Optimal Policies Tend To Seek Power. In Advances in Neural Information Processing Systems, M. Ranzato, A. Beygelzimer, Y. Dauphin, P.S. Liang, and J. Wortman Vaughan (Eds.), Vol. 34. Curran Associates, Inc., 23063\u201323074. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2021\/file\/c26820b8a4c1b3c2aa868d6d57e14a79-Paper.pdf"},{"key":"e_1_3_2_1_117_1","doi-asserted-by":"publisher","DOI":"10.1145\/3375627.3375851"},{"key":"e_1_3_2_1_118_1","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3508"},{"key":"e_1_3_2_1_119_1","unstructured":"Marcus Williams Micah Carroll Adhyyan Narang Constantin Weisser Brendan Murphy and Anca Dragan. 2024. On Targeted Manipulation and Deception when Optimizing LLMs for User Feedback. arXiv:2411.02306 [cs.LG] https:\/\/arxiv.org\/abs\/2411.02306"},{"key":"e_1_3_2_1_120_1","volume-title":"Analysis and Antitrust Implications: A Study in the Economics of Internal Organization","author":"Williamson O.E.","year":"1817","unstructured":"O.E. Williamson. 1973. Markets and Hierarchies, Analysis and Antitrust Implications: A Study in the Economics of Internal Organization. Free Press. http:\/\/www.jstor.org\/stable\/1817092"},{"key":"e_1_3_2_1_121_1","volume-title":"NeurIPS 2023 Workshop on Regulatable ML. https:\/\/openreview.net\/forum?id=R5MTSLPyYZ","author":"Yaghini Mohammad","year":"2023","unstructured":"Mohammad Yaghini, Patty Liu, Franziska Boenisch, and Nicolas Papernot. 2023. Learning to Walk Impartially on the Pareto Frontier of Fairness, Privacy, and Utility. In NeurIPS 2023 Workshop on Regulatable ML. https:\/\/openreview.net\/forum?id=R5MTSLPyYZ"},{"key":"e_1_3_2_1_122_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-naacl.196"},{"key":"e_1_3_2_1_123_1","volume-title":"Group Preference Optimization: Few-Shot Alignment of Large Language Models. In The Twelfth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=DpFeMH4l8Q","author":"Zhao Siyan","year":"2024","unstructured":"Siyan Zhao, John Dang, and Aditya Grover. 2024. Group Preference Optimization: Few-Shot Alignment of Large Language Models. In The Twelfth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=DpFeMH4l8Q"},{"key":"e_1_3_2_1_124_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.630"},{"key":"e_1_3_2_1_125_1","volume-title":"Lin (Eds.)","volume":"33","author":"Zhuang Simon","year":"2020","unstructured":"Simon Zhuang and Dylan Hadfield-Menell. 2020. Consequences of Misaligned AI. 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., 15763\u201315773. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2020\/file\/b607ba543ad05417b8507ee86c54fcb7-Paper.pdf"},{"key":"e_1_3_2_1_126_1","unstructured":"Daniel M. Ziegler Nisan Stiennon Jeffrey Wu Tom B. Brown Alec Radford Dario Amodei Paul Christiano and Geoffrey Irving. 2020. Fine-Tuning Language Models from Human Preferences. arXiv:1909.08593 [cs.CL] https:\/\/arxiv.org\/abs\/1909.08593"},{"key":"e_1_3_2_1_127_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.261"},{"key":"e_1_3_2_1_128_1","unstructured":"Thomas P Zollo Todd Morrill Zhun Deng Jake Snell Toniann Pitassi and Richard Zemel. 2024. Prompt Risk Control: A Rigorous Framework for Responsible Deployment of Large Language Models. In The Twelfth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=5tGGWOijvq"},{"key":"e_1_3_2_1_129_1","unstructured":"Andy Zou Zifan Wang Nicholas Carlini Milad Nasr J. Zico Kolter and Matt Fredrikson. 2023. Universal and Transferable Adversarial Attacks on Aligned Language Models. arXiv:2307.15043 [cs.CL] https:\/\/arxiv.org\/abs\/2307.15043"}],"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\/3805689.3806486","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T18:02:04Z","timestamp":1782756124000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3805689.3806486"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,25]]},"references-count":129,"alternative-id":["10.1145\/3805689.3806486","10.1145\/3805689"],"URL":"https:\/\/doi.org\/10.1145\/3805689.3806486","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"}}]}}