{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T19:49:19Z","timestamp":1782762559991,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":75,"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"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,6,25]]},"DOI":"10.1145\/3805689.3812420","type":"proceedings-article","created":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T17:52:08Z","timestamp":1782755528000},"page":"622-639","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Relative Principals, Pluralistic Alignment, and the Structural Value Alignment Problem"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1724-3434","authenticated-orcid":false,"given":"Travis","family":"LaCroix","sequence":"first","affiliation":[{"name":"Department of Philosophy, Durham University, Durham, United Kingdom, and Schwartz Reisman Institute for Technology and Society, University of Toronto, Toronto, 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":"Concrete Problems in AI Safety. arXiv 1606.06565","author":"Amodei Dario","year":"2016","unstructured":"Dario Amodei, Chris Olah, Jacob Steinhardt, Paul Christiano, John Schulman, and Dan Man\u00e9. 2016. Concrete Problems in AI Safety. arXiv 1606.06565 (2016), 1\u201329. https:\/\/arxiv.org\/abs\/1606.06565."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10670-025-01010-x"},{"key":"e_1_3_2_1_3_1","volume-title":"DICES Dataset: Diversity in Conversational AI Evaluation for Safety. arXiv 2306.11247","author":"Aroyo Lora","year":"2023","unstructured":"Lora Aroyo, Alex S. Taylor, Mark Diaz, Christopher M. Homan, Alicia Parrish, Greg Serapio-Garcia, Vinodkumar Prabhakaran, and Ding Wang. 2023. DICES Dataset: Diversity in Conversational AI Evaluation for Safety. arXiv 2306.11247 (2023), 1\u201322. https:\/\/arxiv.org\/abs\/2306.11247."},{"key":"e_1_3_2_1_4_1","unstructured":"Yoshua Bengio. 2023. How Rogue AIs may Arise. https:\/\/yoshuabengio.org\/en\/blog\/how-rogue-ais-may-arise."},{"key":"e_1_3_2_1_5_1","volume-title":"Superintelligent Agents Pose Catastrophic Risks: Can Scientist AI Offer a Safer Path? arXiv 2502.15657","author":"Bengio Yoshua","year":"2025","unstructured":"Yoshua Bengio, Michael Cohen, Damiano Fornasiere, Joumana Ghosn, Pietro Greiner, Matt MacDermott, S\u00f6ren Mindermann, Adam Oberman, Jesse Richardson, Oliver Richardson, Marc-Antoine Rondeau, Pierre-Luc St-Charles, and David Williams-King. 2025. Superintelligent Agents Pose Catastrophic Risks: Can Scientist AI Offer a Safer Path? arXiv 2502.15657 (2025), 1\u201358. https:\/\/arxiv.org\/abs\/2502.15657."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.4324\/9781003320609-52"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-024-56648-4"},{"key":"e_1_3_2_1_8_1","volume-title":"Science fiction and philosophy: from time travel to superintelligence","author":"Bostrom Nick","unstructured":"Nick Bostrom. 2003. Ethical issues in advanced artificial intelligence. In Science fiction and philosophy: from time travel to superintelligence, Susan Schneider (Ed.). Wiley & Blackwell, West Sussex, 277\u2013284."},{"key":"e_1_3_2_1_9_1","volume-title":"Superintelligence: Paths, Dangers, Strategies","author":"Bostrom Nick","year":"2014","unstructured":"Nick Bostrom. 2014. Superintelligence: Paths, Dangers, Strategies. Oxford University Press, Oxford."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/14234.001.0001"},{"key":"e_1_3_2_1_11_1","volume-title":"The Alignment Problem: Machine Learning and Human Values","author":"Christian Brian","unstructured":"Brian Christian. 2020. The Alignment Problem: Machine Learning and Human Values. W. W. Norton & Company, New York."},{"key":"e_1_3_2_1_12_1","volume-title":"Social Choice Should Guide AI Alignment in Dealing with Diverse Human Feedback. arXiv","author":"Conitzer Vincent","year":"2024","unstructured":"Vincent Conitzer, Rachel Freedman, Jobst Heitzig, Wesley H. Holliday, Bob M. Jacobs, Nathan Lambert, Milan Moss\u00e9, Eric Pacuit, Stuart Russell, Hailey Schoelkopf, and Others. 2024. Social Choice Should Guide AI Alignment in Dealing with Diverse Human Feedback. arXiv (2024), 1\u201315. https:\/\/arxiv.org\/abs\/2404.10271."},{"key":"e_1_3_2_1_13_1","volume-title":"Atlas of AI","author":"Crawford Kate","unstructured":"Kate Crawford. 2021. Atlas of AI. Yale University Press, New Haven, CT."},{"key":"e_1_3_2_1_14_1","volume-title":"Tasra: A taxonomy and analysis of societal-scale risks from ai. arXiv 2306.06924","author":"Critch Andrew","year":"2023","unstructured":"Andrew Critch and Stuart Russell. 2023. Tasra: A taxonomy and analysis of societal-scale risks from ai. arXiv 2306.06924 (2023), 1\u201318. https:\/\/arxiv.org\/abs\/2306.06924."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00449"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-22887-2_35"},{"key":"e_1_3_2_1_17_1","volume-title":"Value-laden Disciplinary Shifts in Machine Learning. arXiv","author":"Dotan Ravit","year":"1912","unstructured":"Ravit Dotan and Smitha Milli. 2019. Value-laden Disciplinary Shifts in Machine Learning. arXiv 1912.01172 (2019), 1\u201310. https:\/\/arxiv.org\/abs\/1912.01172."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1086\/392855"},{"key":"e_1_3_2_1_19_1","volume-title":"Impossibility and Uncertainty Theorems in AI Value Alignment (or why your AGI should not have a utility function). arXiv","author":"Eckersley Peter","year":"1901","unstructured":"Peter Eckersley. 2019. Impossibility and Uncertainty Theorems in AI Value Alignment (or why your AGI should not have a utility function). arXiv 1901.00064 (2019), 1\u201313. https:\/\/arxiv.org\/abs\/1901.00064."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.2307\/258191"},{"key":"e_1_3_2_1_21_1","volume-title":"Observation Interference in Partially Observable Assistance Games. arXiv 2412.17797","author":"Emmons Scott","year":"2025","unstructured":"Scott Emmons, Caspar Oesterheld, Vincent Conitzer, and Stuart Russell. 2025. Observation Interference in Partially Observable Assistance Games. arXiv 2412.17797 (2025), 1\u201326. https:\/\/arxiv.org\/abs\/2412.17797."},{"key":"e_1_3_2_1_22_1","volume-title":"Proceedings of the 1st Conference on Fairness, Accountability and Transparency (Proceedings of Machine Learning Research","volume":"171","author":"Ensign Danielle","year":"2018","unstructured":"Danielle Ensign, Sorelle A. Friedler, Scott Neville, Carlos Scheidegger, and Suresh Venkatasubramanian. 2018. Runaway Feedback Loops in Predictive Policing. In Proceedings of the 1st Conference on Fairness, Accountability and Transparency (Proceedings of Machine Learning Research, Vol. 81), Sorelle A. Friedler and Christo Wilson (Eds.). PMLR, 160\u2013171."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3715275.3732146"},{"key":"e_1_3_2_1_24_1","volume-title":"Dragan","author":"Fisac Jaime F.","year":"2020","unstructured":"Jaime F. Fisac, Monica A. Gates, Jessica B. Hamrick, Chang Liu, Dylan Hadfield-Menell, Malayandi Palaniappan, Dhruv Malik, S. Shankar Sastry, Thomas L. Griffiths, and Anca D. Dragan. 2020. Pragmatic-Pedagogic Value Alignment. In Springer Proceedings in Advanced Robotics, N. Amato, G. Hager, S. Thomas, and M. Torres-Torriti (Eds.). Vol. 10. Springer, 49\u201357."},{"key":"e_1_3_2_1_25_1","unstructured":"Future of Life Institute. 2017. Asilomar AI Principles. https:\/\/futureoflife.org\/open-letter\/ai-principles\/."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11023-020-09539-2"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11098-025-02300-4"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i26.34940"},{"key":"e_1_3_2_1_29_1","volume-title":"On the Dangers of Stochastic Pollocks. PhilArchive","author":"Goetze Trystan S.","year":"2024","unstructured":"Trystan S. Goetze. 2024. AI Art is Theft: Labour, Extraction, and Exploitation\u2014Or, On the Dangers of Stochastic Pollocks. PhilArchive (2024). Unpublished preprint of 10 January 2024. https:\/\/philarchive.org\/rec\/GOEAAI-2."},{"key":"e_1_3_2_1_30_1","volume-title":"Genetic Algorithms and Simulated Annealing (Research Notes in Artificial Intelligence)","author":"Goldberg David E.","unstructured":"David E. Goldberg. 1987. Simple genetic algorithms and the minimal deceptive problem. In Genetic Algorithms and Simulated Annealing (Research Notes in Artificial Intelligence), Lawrence D. Davis (Ed.). Morgan Kaufmann Publishers, Burlington, MA, 74\u201388."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-31388-2_6"},{"key":"e_1_3_2_1_32_1","volume-title":"Kayur Patel, Jeffrey T. Hancock, Tatsunori Hashimoto, and Michael S.","author":"Gordon Mitchell L.","year":"2022","unstructured":"Mitchell L. Gordon, Michelle S. Lam, Joon Sung Park, Kayur Patel, Jeffrey T. Hancock, Tatsunori Hashimoto, and Michael S. Bernstein. 2022. Jury Learning: Integrating Dissenting Voices into Machine Learning Models. arXiv 2202.02950 (2022), 1\u201319. https:\/\/arxiv.org\/abs\/2202.02950."},{"key":"e_1_3_2_1_33_1","volume-title":"Gray and Siddharth Suri","author":"Mary","year":"2019","unstructured":"Mary L. Gray and Siddharth Suri. 2019. Ghost Work: How to Stop Silicon Valley from Building a New Global Underclass. Eamon Dolan Books, New York."},{"key":"e_1_3_2_1_34_1","volume-title":"The Principal-Agent Alignment Problem in Artificial Intelligence. Ph. D. Dissertation. EECS Department","author":"Hadfield-Menell Dylan","year":"2021","unstructured":"Dylan Hadfield-Menell. 2021. The Principal-Agent Alignment Problem in Artificial Intelligence. Ph. D. Dissertation. EECS Department, University of California, Berkeley. http:\/\/www2.eecs.berkeley.edu\/Pubs\/TechRpts\/2021\/EECS-2021-207.html."},{"key":"e_1_3_2_1_35_1","volume-title":"NIPS'16: Proceedings of the 30th International Conference on Neural Information Processing Systems, Daniel D","author":"Hadfield-Menell Dylan","unstructured":"Dylan Hadfield-Menell, Anca Dragan, Pieter Abbeel, and Stuart Russell. 2016. Cooperative inverse reinforcement learning. In NIPS'16: Proceedings of the 30th International Conference on Neural Information Processing Systems, Daniel D. Lee, Ulrike von Luxburg, Roman Garnett, Masashi Sugiyama, and Isabelle Guyon (Eds.). Association for Computing Machinery, 3916\u20133924."},{"key":"e_1_3_2_1_36_1","volume-title":"The Off-Switch Game. arXiv 1611.08219","author":"Hadfield-Menell Dylan","year":"2017","unstructured":"Dylan Hadfield-Menell, Anca Dragan, Pieter Abbeel, and Stuart Russell. 2017. The Off-Switch Game. arXiv 1611.08219 (2017), 1\u20138. https:\/\/arxiv.org\/abs\/1611.08219."},{"key":"e_1_3_2_1_37_1","volume-title":"Hadfield","author":"Hadfield-Menell Dylan","year":"2019","unstructured":"Dylan Hadfield-Menell and Gillian K. Hadfield. 2019. Incomplete Contracting and AI Alignment. In AIES '19: Proceedings of the 2019 AAAI\/ACM Conference on AI, Ethics, and Society, Vincent Conitzer, Gillian Hadfield, and Shannon Vallor (Eds.). Association for Computing Machinery, New York, 417\u2013422."},{"key":"e_1_3_2_1_38_1","volume-title":"Proceedings of the ACM Conference on Human Factors in Computing Systems (CHI)","author":"Hamidi Foad","year":"2018","unstructured":"Foad Hamidi, Morgan Klaus Scheuerman, and Stacy M. Branham. 2018. Gender recognition or gender reductionism?: The social implications of embedded gender recognition systems. Proceedings of the ACM Conference on Human Factors in Computing Systems (CHI) (2018), 1\u201313."},{"key":"e_1_3_2_1_39_1","volume-title":"Aspects of Scientific Explanation","author":"Hempel Carl","unstructured":"Carl Hempel. 1965. Aspects of Scientific Explanation. Free Press, New York."},{"key":"e_1_3_2_1_40_1","volume-title":"Aligning AI With Shared Human Values. arXiv","author":"Hendrycks Dan","year":"2008","unstructured":"Dan Hendrycks, Collin Burns, Steven Basart, Andrew Critch, Jerry Li, Dawn Song, and Jacob Steinhardt. 2023. Aligning AI With Shared Human Values. arXiv 2008.02275 (2023), 1\u201329. https:\/\/arxiv.org\/abs\/2008.02275."},{"key":"e_1_3_2_1_41_1","unstructured":"Dan Hendrycks and Mantas Mazeika. 2022. X-risk analysis for AI research. arXiv 2206.05862(2022) 1\u201336. https:\/\/arxiv.org\/abs\/2206.05862."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1080\/1369118X.2019.1573912"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3630106.3658979"},{"key":"e_1_3_2_1_44_1","volume-title":"Risks from Learned Optimization in Advanced Machine Learning Systems. arXiv","author":"Hubinger Evan","year":"1906","unstructured":"Evan Hubinger, Chris van Merwijk, Vladimir Mikulik, Joar Skalse, and Scott Garrabrant. 2021. Risks from Learned Optimization in Advanced Machine Learning Systems. arXiv 1906.01820 (2021), 1\u201339. https:\/\/arxiv.org\/abs\/1906.01820."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1016\/0304-405X(76)90026-X"},{"key":"e_1_3_2_1_46_1","volume-title":"Aidan O'Gara, Hua Xu, Brian Tse, Jie Fu, Stephen McAleer, Yaodong Yang, Yizhou Wang, Song-Chun Zhu, Yike Guo, and Wen Gao.","author":"Ji Jiaming","year":"2025","unstructured":"Jiaming Ji, Tianyi Qiu, Boyuan Chen, Borong Zhang, Hantao Lou, Kaile Wang, Yawen Duan, Zhonghao He, Lukas Vierling, Donghai Hong, Jiayi Zhou, Zhaowei Zhang, Fanzhi Zeng, Juntao Dai, Xuehai Pan, Kwan Yee Ng, Aidan O'Gara, Hua Xu, Brian Tse, Jie Fu, Stephen McAleer, Yaodong Yang, Yizhou Wang, Song-Chun Zhu, Yike Guo, and Wen Gao. 2025. AI Alignment: A Comprehensive Survey. arXiv 2310.19852 (2025), 1\u2013105. https:\/\/arxiv.org\/abs\/2310.19852."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.2307\/255378"},{"key":"e_1_3_2_1_48_1","volume-title":"Hale","author":"Kirk Hannah Rose","year":"2024","unstructured":"Hannah Rose Kirk, Alexander Whitefield, Paul R\u00f6ttger, Andrew Bean, Katerina Margatina, Juan Ciro, Rafael Mosquera, Max Bartolo, Adina Williams, He He, Bertie Vidgen, and Scott A. Hale. 2024. The PRISM Alignment Project: What Participatory, Representative and Individualised Human Feedback Reveals About the Subjective and Multicultural Alignment of Large Language Models. arXiv 2404.16019 (2024), 1\u2013107. https:\/\/arXiv.org\/abs\/2404.16019."},{"key":"e_1_3_2_1_49_1","volume-title":"Artificial Intelligence and the Value Alignment Problem: A Philosophical Introduction","author":"LaCroix Travis","unstructured":"Travis LaCroix. 2025. Artificial Intelligence and the Value Alignment Problem: A Philosophical Introduction. Broadview Press."},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1007\/s43681-025-00703-x"},{"key":"e_1_3_2_1_51_1","volume-title":"The Theory of Incentives: The Principal-Agent Model","author":"Laffont Jean-Jacques","unstructured":"Jean-Jacques Laffont and David Martimort. 2002. The Theory of Incentives: The Principal-Agent Model. Princeton University Press, Princeton."},{"key":"e_1_3_2_1_52_1","volume-title":"Proceedings of the Eleventh International Conference on Artificial Life (ALIFE XI). The MIT Press","author":"Lehman Joel","unstructured":"Joel Lehman and Kenneth O. Stanley. 2008. Exploiting Open-Endedness to Solve Problems Through the Search for Novelty. In Proceedings of the Eleventh International Conference on Artificial Life (ALIFE XI). The MIT Press, Cambridge, MA, 329\u2013336."},{"key":"e_1_3_2_1_53_1","volume-title":"Power Hungry Processing: Watts Driving the Cost of AI Deployment? arXiv 2311.16863","author":"Luccioni Alexandra Sasha","year":"2023","unstructured":"Alexandra Sasha Luccioni, Yacine Jernite, and Emma Strubell. 2023. Power Hungry Processing: Watts Driving the Cost of AI Deployment? arXiv 2311.16863 (2023), 1\u201320. https:\/\/arxiv.org\/abs\/2311.16863."},{"key":"e_1_3_2_1_54_1","first-page":"1","article-title":"Estimating the Carbon Footprint of BLOOM, a 176B Parameter Language Model","volume":"24","author":"Luccioni Alexandra Sasha","year":"2023","unstructured":"Alexandra Sasha Luccioni, Sylvain Viguier, and Anne-Laure Ligozat. 2023. Estimating the Carbon Footprint of BLOOM, a 176B Parameter Language Model. Journal of Machine Learning Research 24, 253 (2023), 1\u201315.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1740-9713.2016.00960.x"},{"key":"e_1_3_2_1_56_1","volume-title":"Resisting AI: An Anti-fascist Approach to Artificial Intelligence","author":"McQuillan Dan","year":"2022","unstructured":"Dan McQuillan. 2022. Resisting AI: An Anti-fascist Approach to Artificial Intelligence. Bristol University Press, Bristol."},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1145\/3492853"},{"key":"e_1_3_2_1_58_1","volume-title":"Proceedings of the First European Conference on Artificial Life, F. J. Varela and P. Bourgine (Eds.). The MIT Press","author":"Mitchell Melanie","unstructured":"Melanie Mitchell, Stephanie Forrest, and John H. Holland. 1992. The royal road for genetic algorithms: Fitness landscapes and GA performance. In Proceedings of the First European Conference on Artificial Life, F. J. Varela and P. Bourgine (Eds.). The MIT Press, Cambridge, MA, 1\u201311."},{"key":"e_1_3_2_1_59_1","volume-title":"The Alignment Problem from a Deep Learning Perspective. arXiv 2209.00626","author":"Ngo Richard","year":"2023","unstructured":"Richard Ngo, Lawrence Chen, and S\u00f6ren Mindermann. 2023. The Alignment Problem from a Deep Learning Perspective. arXiv 2209.00626 (2023), 1\u201321. https:\/\/arxiv.org\/abs\/2209.00626."},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1201\/9781351251389-3"},{"key":"e_1_3_2_1_61_1","volume-title":"Weapons of Math Destruction: How Big Data Increases Inequality and Threatens Democracy","author":"O'Neil Cathy","unstructured":"Cathy O'Neil. 2016. Weapons of Math Destruction: How Big Data Increases Inequality and Threatens Democracy. Broadway Books, New York."},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00971"},{"key":"e_1_3_2_1_63_1","volume-title":"Bakker","author":"Poole-Dayan Elinor","year":"2026","unstructured":"Elinor Poole-Dayan, Jiayi Wu, Taylor Sorensen, Jiaxin Pei, and Michiel A. Bakker. 2026. Benchmarking Overton Pluralism in LLMs. arXiv 2512.01351 (2026), 1\u201340. https:\/\/arxiv.org\/abs\/2512.01351."},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1201\/9781351251389-21"},{"key":"e_1_3_2_1_65_1","volume-title":"arXiv 2401.10899","author":"Raji Inioluwa Deborah","year":"2023","unstructured":"Inioluwa Deborah Raji and Roel Dobbe. 2023. Concrete Problems in AI Safety, Revisited. arXiv 2401.10899 (2023), 2023. https:\/\/arxiv.org\/abs\/2401.10899\/."},{"key":"e_1_3_2_1_66_1","volume-title":"Saving Face: Investigating the Ethical Concerns of Facial Recognition Auditing. arXiv","author":"Raji Inioluwa Deborah","year":"2020","unstructured":"Inioluwa Deborah Raji, Timnit Gebru, Margaret Mitchell, Joy Buolamwini, Joonseok Lee, and Emily Denton. 2020. Saving Face: Investigating the Ethical Concerns of Facial Recognition Auditing. arXiv 2001.00964 (2020), 1\u20137. https:\/\/arxiv.org\/abs\/2001.00964."},{"key":"e_1_3_2_1_67_1","volume-title":"Human Compatible: Artificial Intelligence and the Problem of Control","author":"Russell Stuart","year":"2019","unstructured":"Stuart Russell. 2019. Human Compatible: Artificial Intelligence and the Problem of Control. Viking, New York."},{"key":"e_1_3_2_1_68_1","volume-title":"34th Conference on Neural Information Processing Systems (NeurIPS 2020) - Workshop on Cooperative AI","author":"Shah Rohin","year":"2020","unstructured":"Rohin Shah, Pedro Freire, Neel Alex, Rachel Freedman, Dmitrii Krasheninnikov, Lawrence Chan, Michael Dennis, Pieter Abbeel, Anca Dragan, and Stuart Russell. 2020. Benefits of Assistance over Reward Learning. 34th Conference on Neural Information Processing Systems (NeurIPS 2020) - Workshop on Cooperative AI (2020)."},{"key":"e_1_3_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.1186\/s13040-018-0182-8"},{"key":"e_1_3_2_1_70_1","volume-title":"Distributional Preference Learning: Understanding and Accounting for Hidden Context in RLHF. arXiv 2312.08358","author":"Siththaranjan Anand","year":"2024","unstructured":"Anand Siththaranjan, Cassidy Laidlaw, and Dylan Hadfield-Menell. 2024. Distributional Preference Learning: Understanding and Accounting for Hidden Context in RLHF. arXiv 2312.08358 (2024), 1\u201326. https:\/\/arxiv.org\/abs\/2312.08358."},{"key":"e_1_3_2_1_71_1","volume-title":"Value Kaleidoscope: Engaging AI with Pluralistic Human Values, Rights, and Duties. arXiv 2309.00779","author":"Sorensen Taylor","year":"2024","unstructured":"Taylor Sorensen, Liwei Jiang, Jena Hwang, Sydney Levine, Valentina Pyatkin, Peter West, Nouha Dziri, Ximing Lu, Kavel Rao, Chandra Bhagavatula, and Others. 2024. Value Kaleidoscope: Engaging AI with Pluralistic Human Values, Rights, and Duties. arXiv 2309.00779 (2024). https:\/\/arxiv.org\/abs\/2309.00779."},{"key":"e_1_3_2_1_72_1","volume-title":"Andre Ye, Liwei Jiang, Ximing Lu, Nouha Dziri, Tim Althoff, and Yejin Choi.","author":"Sorensen Taylor","year":"2024","unstructured":"Taylor Sorensen, Jared Moore, Jillian Fisher, Mitchell Gordon, Niloofar Mireshghallah, Christopher Michael Rytting, Andre Ye, Liwei Jiang, Ximing Lu, Nouha Dziri, Tim Althoff, and Yejin Choi. 2024. A roadmap to pluralistic alignment. arXiv 2402.05070 (2024), 1\u201323. https:\/\/arxiv.org\/abs\/2402.05070."},{"key":"e_1_3_2_1_73_1","volume-title":"Being human in the age of artificial intelligence","author":"Tegmark Max","unstructured":"Max Tegmark. 2018. Life 3.0: Being human in the age of artificial intelligence. Vintage, New York."},{"key":"e_1_3_2_1_74_1","volume-title":"AI can help humans find common ground in democratic deliberation. Science 386, 6719","author":"Tessler Michael Henry","year":"2024","unstructured":"Michael Henry Tessler, Michiel A. Bakker, Daniel Jarrett, Hannah Sheahan, Martin J. Chadwick, Raphael Koster, Georgina Evans, Lucy Campbell-Gillingham, Tantum Collins, David C. Parkes, Matthew Botvinick, and Christopher Summerfield. 2024. AI can help humans find common ground in democratic deliberation. Science 386, 6719 (2024), eadq2852."},{"key":"e_1_3_2_1_75_1","volume-title":"Complex value systems in friendly AI. 6830","author":"Yudkowsky Eliezer","year":"2011","unstructured":"Eliezer Yudkowsky. 2011. Complex value systems in friendly AI. 6830 (2011), 388\u2013393."}],"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\/3805689.3812420","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T19:26:12Z","timestamp":1782761172000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3805689.3812420"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,25]]},"references-count":75,"alternative-id":["10.1145\/3805689.3812420","10.1145\/3805689"],"URL":"https:\/\/doi.org\/10.1145\/3805689.3812420","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"}}]}}