{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T22:23:53Z","timestamp":1782858233643,"version":"3.54.5"},"reference-count":29,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100005950","name":"Hong Kong University of Science and Technology","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100005950","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["AI Ethics"],"published-print":{"date-parts":[[2025,2]]},"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:p>Value alignment is essential for ensuring that AI systems act in ways that are consistent with human values. Existing approaches, such as reinforcement learning with human feedback and constitutional AI, however, exhibit power asymmetries and lack transparency. These \u201cauthoritarian\u201d approaches fail to adequately accommodate a broad array of human opinions, raising concerns about whose values are being prioritized. In response, we introduce the Dynamic Value Alignment approach, theoretically grounded in the principles of parallel constraint satisfaction, which models moral reasoning as a dynamic process that balances multiple value principles. Our approach also enhances users\u2019 moral and epistemic agency by granting users greater control over the values that influence AI behavior. As a more user-centric, transparent, and participatory framework for AI ethics, our approach not only addresses the democratic deficits inherent in current practices but also ensures that AI systems are flexibly aligned with a diverse array of human values.<\/jats:p>","DOI":"10.1007\/s43681-024-00624-1","type":"journal-article","created":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T10:42:44Z","timestamp":1733136164000},"page":"11-18","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":13,"title":["Democratizing value alignment: from authoritarian to democratic AI ethics"],"prefix":"10.1007","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2469-8944","authenticated-orcid":false,"given":"Linus Ta-Lun","family":"Huang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4582-4973","authenticated-orcid":false,"given":"Gleb","family":"Papyshev","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5570-2163","authenticated-orcid":false,"given":"James K.","family":"Wong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,12,2]]},"reference":[{"key":"624_CR1","unstructured":"Anthropic: Collective Constitutional AI: Aligning a Language Model with Public Input. (2023). https:\/\/www.anthropic.com\/news\/collective-constitutional-ai-aligning-a-language-model-with-public-input"},{"key":"624_CR2","doi-asserted-by":"crossref","first-page":"59","DOI":"10.1038\/s41586-018-0637-6","volume":"563","author":"E Awad","year":"2018","unstructured":"Awad, E., Dsouza, S., Kim, R., Schulz, J., Henrich, J., Shariff, A., Bonnefon, J., Rahwan, I.: The Moral Machine Experiment. Nature. 563, 59\u201364 (2018)","journal-title":"Nature"},{"key":"624_CR3","doi-asserted-by":"publisher","unstructured":"Bai, Y., Kadavath, S., Kundu, S., Askell, A., Kernion, J., Jones, A., Chen, A., Goldie, A., Mirhoseini, A., McKinnon, C., Chen, C., Olsson, C., Olah, C., Hernandez, D., Drain, D., Ganguli, D., Li, D., Tran-Johnson, E., Perez, E., Kaplan, J.: Constitutional AI: Harmlessness from AI Feedback (arXiv:2212.08073). arXiv. (2022). https:\/\/doi.org\/10.48550\/arXiv.2212.08073","DOI":"10.48550\/arXiv.2212.08073"},{"key":"624_CR4","unstructured":"Burnor, R., Raley, Y.: Ethical Choices: An Introduction to Moral Philosophy with Cases (2nd edition). Oxford: Oxford University Press. (2018)"},{"key":"624_CR5","doi-asserted-by":"publisher","unstructured":"Casper, S., Davies, X., Shi, C., Gilbert, T.K., Scheurer, J., Rando, J., Freedman, R., Korbak, T., Lindner, D., Freire, P., Wang, T., Marks, S., Segerie, C.-R., Carroll, M., Peng, A., Christoffersen, P., Damani, M., Slocum, S., Anwar, U., Hadfield-Menell, D.: Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback (arXiv:2307.15217). arXiv. (2023). https:\/\/doi.org\/10.48550\/arXiv.2307.15217","DOI":"10.48550\/arXiv.2307.15217"},{"key":"624_CR6","doi-asserted-by":"publisher","unstructured":"Chaudhari, S., Aggarwal, P., Murahari, V., Rajpurohit, T., Kalyan, A., Narasimhan, K., Deshpande, A., da Silva, B.C.: RLHF Deciphered: A Critical Analysis of Reinforcement Learning from Human Feedback for LLMs(arXiv:2404.08555). arXiv. (2024). https:\/\/doi.org\/10.48550\/arXiv.2404.08555","DOI":"10.48550\/arXiv.2404.08555"},{"key":"624_CR7","doi-asserted-by":"publisher","unstructured":"Conitzer, V., Freedman, R., Heitzig, J., Holliday, W.H., Jacobs, B.M., Lambert, N., Moss\u00e9, M., Pacuit, E., Russell, S., Schoelkopf, H., Tewolde, E., Zwicker, W.S.: Social Choice for AI Alignment: Dealing with Diverse Human Feedback (arXiv:2404.10271). arXiv. (2024). https:\/\/doi.org\/10.48550\/arXiv.2404.10271","DOI":"10.48550\/arXiv.2404.10271"},{"issue":"3","key":"624_CR8","doi-asserted-by":"crossref","first-page":"365","DOI":"10.1007\/s10506-017-9211-z","volume":"25","author":"C Contissa","year":"2017","unstructured":"Contissa, C., Lagioia, F., Sartor, G.: The ethical knob: ethically-customisable automated vehicles and the law. Artif. Intell. Law. 25(3), 365\u2013378 (2017)","journal-title":"Artif. Intell. Law"},{"issue":"3","key":"624_CR9","doi-asserted-by":"crossref","first-page":"324","DOI":"10.1177\/1474885115587480","volume":"17","author":"M Festenstein","year":"2015","unstructured":"Festenstein, M.: Self-censorship for democrats. Eur. J. Political Theory. 17(3), 324\u2013342 (2015)","journal-title":"Eur. J. Political Theory"},{"key":"624_CR10","doi-asserted-by":"crossref","unstructured":"Fischer, J.M., Ravizza, M.: Responsibility and control: A theory of moral responsibility. Cambridge University Press (2000)","DOI":"10.2307\/2653660"},{"key":"624_CR12","first-page":"5","volume":"5","author":"P Foot","year":"1967","unstructured":"Foot, P.: The problem of abortion and the doctrine of double effect. Oxf. Rev. 5, 5\u201315 (1967)","journal-title":"Oxf. Rev."},{"key":"624_CR11","doi-asserted-by":"crossref","DOI":"10.1093\/acprof:oso\/9780198237907.001.0001","volume-title":"Epistemic Injustice: Power and the Ethics of Knowing","author":"M Fricker","year":"2007","unstructured":"Fricker, M.: Epistemic Injustice: Power and the Ethics of Knowing. Oxford University Press, Oxford (2007)"},{"issue":"1","key":"624_CR13","doi-asserted-by":"publisher","first-page":"183","DOI":"10.48550\/arXiv.2312.14925","volume":"79","author":"J Gurney","year":"2016","unstructured":"Gurney, J.: Crashing into the unknown: an examination of crash-optimization algorithms through the two lanes of ethics and law. Albany Law Rev. 79(1), 183\u2013267 (2016). https:\/\/doi.org\/10.48550\/arXiv.2312.14925","journal-title":"Albany Law Rev."},{"key":"624_CR14","unstructured":"Kaufmann, T., Weng, P., Bengs, V., H\u00fcllermeier, E.: A survey of reinforcement learning from human feedback. arXiv. (2023)."},{"key":"624_CR15","doi-asserted-by":"publisher","unstructured":"Kundu, S., Bai, Y., Kadavath, S., Askell, A., Callahan, A., Chen, A., Goldie, A., Balwit, A., Mirhoseini, A., McLean, B., Olsson, C., Evraets, C., Tran-Johnson, E., Durmus, E., Perez, E., Kernion, J., Kerr, J., Ndousse, K., Nguyen, K., Kaplan, J.: Specific versus General Principles for Constitutional AI (arXiv:2310.13798). arXiv. (2023). https:\/\/doi.org\/10.48550\/arXiv.2310.13798","DOI":"10.48550\/arXiv.2310.13798"},{"key":"624_CR16","doi-asserted-by":"publisher","unstructured":"Lee, K., Hwang, D., Park, S., Jang, Y., Lee, M.: Reinforcement Learning from Reflective Feedback (RLRF): Aligning and Improving LLMs via Fine-Grained Self-Reflection (arXiv:2403.14238). arXiv. (2024). https:\/\/doi.org\/10.48550\/arXiv.2403.14238","DOI":"10.48550\/arXiv.2403.14238"},{"key":"624_CR17","doi-asserted-by":"publisher","unstructured":"Li, A., Xiao, Q., Cao, P., Tang, J., Yuan, Y., Zhao, Z., Chen, X., Zhang, L., Li, X., Yang, K., Guo, W., Gan, Y., Yu, X., Wang, D., Shan, Y.: HRLAIF: Improvements in Helpfulness and Harmlessness in Open-domain Reinforcement Learning From AI Feedback (arXiv:2403.08309). arXiv. (2024). https:\/\/doi.org\/10.48550\/arXiv.2403.08309","DOI":"10.48550\/arXiv.2403.08309"},{"key":"624_CR18","unstructured":"List, C.: Social Choice Theory. In E. N. Zalta (Ed.), The Stanford Encyclopedia of Philosophy (Winter 2013). Metaphysics Research Lab, Stanford University. (2013). https:\/\/plato.stanford.edu\/archives\/win2013\/entries\/social-choice\/"},{"key":"624_CR19","volume-title":"Law\u2019s Relations: A Relational Theory of Self, Autonomy, and Law","author":"J Nedelsky","year":"2013","unstructured":"Nedelsky, J.: Law\u2019s Relations: A Relational Theory of Self, Autonomy, and Law. Oxford University Press, Oxford (2013)"},{"issue":"5","key":"624_CR20","doi-asserted-by":"crossref","first-page":"1275","DOI":"10.1007\/s10677-016-9745-2","volume":"19","author":"S Nyholm","year":"2016","unstructured":"Nyholm, S., Smids, J.: The Ethics of Accident-algorithms for Self-driving cars: An Applied Trolley Problem? Ethical Theory Moral. Pract. 19(5), 1275\u20131289 (2016)","journal-title":"Ethical Theory Moral. Pract."},{"key":"624_CR21","doi-asserted-by":"publisher","unstructured":"Ouyang, L., Wu, J., Jiang, X., Almeida, D., Wainwright, C.L., Mishkin, P., Zhang, C., Agarwal, S., Slama, K., Ray, A., Schulman, J., Hilton, J., Kelton, F., Miller, L., Simens, M., Askell, A., Welinder, P., Christiano, P., Leike, J., Lowe, R.: Training language models to follow instructions with human feedback (arXiv:2203.02155). arXiv. (2022). https:\/\/doi.org\/10.48550\/arXiv.2203.02155","DOI":"10.48550\/arXiv.2203.02155"},{"key":"624_CR22","volume-title":"Unconditional Equals","author":"A Phillips","year":"2021","unstructured":"Phillips, A.: Unconditional Equals. Princeton University Press, Princeton (2021)"},{"key":"624_CR23","doi-asserted-by":"crossref","DOI":"10.1017\/9781009255189","volume-title":"Political Theory of the Digital Age: Where Artificial Intelligence Might Take Us","author":"M Risse","year":"2023","unstructured":"Risse, M.: Political Theory of the Digital Age: Where Artificial Intelligence Might Take Us. Cambridge University Press, Cambridge (2023)"},{"key":"624_CR24","doi-asserted-by":"crossref","unstructured":"Simon, D., Holyoak, K.J.: Structural Dynamics of Cognition: From consistency theories to constraint satisfaction. In: The Dynamic Perspective in Personality and Social Psychology. Psychology (2003)","DOI":"10.1207\/S15327957PSPR0604_03"},{"issue":"4","key":"624_CR25","doi-asserted-by":"publisher","first-page":"405","DOI":"10.1080\/09515089808573270","volume":"11","author":"P Thagard","year":"1998","unstructured":"Thagard, P.: Ethical coherence. Philosophical Psychol. 11(4), 405\u2013422 (1998). https:\/\/doi.org\/10.1080\/09515089808573270","journal-title":"Philosophical Psychol."},{"key":"624_CR26","doi-asserted-by":"crossref","unstructured":"Thagard, P.: Coherence in Thought and Action. MIT Press (2000)","DOI":"10.7551\/mitpress\/1900.001.0001"},{"issue":"2","key":"624_CR27","doi-asserted-by":"crossref","first-page":"204","DOI":"10.5840\/monist197659224","volume":"59","author":"J Thomson","year":"1976","unstructured":"Thomson, J.: Killing, letting die, and the trolley problem. Monist. 59(2), 204\u2013217 (1976)","journal-title":"Monist"},{"key":"624_CR28","doi-asserted-by":"crossref","first-page":"1395","DOI":"10.2307\/796133","volume":"94","author":"J Thomson","year":"1985","unstructured":"Thomson, J.: The Trolley Problem. Yale Law J. 94, 1395\u20131415 (1985)","journal-title":"Yale Law J."},{"key":"624_CR29","doi-asserted-by":"crossref","DOI":"10.1093\/0198297556.001.0001","volume-title":"Inclusion and Democracy","author":"I Young","year":"2002","unstructured":"Young, I.: Inclusion and Democracy. Oxford University Press, Oxford (2002)"}],"container-title":["AI and Ethics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s43681-024-00624-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s43681-024-00624-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s43681-024-00624-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,24]],"date-time":"2025-03-24T07:08:21Z","timestamp":1742800101000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s43681-024-00624-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,2]]},"references-count":29,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,2]]}},"alternative-id":["624"],"URL":"https:\/\/doi.org\/10.1007\/s43681-024-00624-1","relation":{},"ISSN":["2730-5953","2730-5961"],"issn-type":[{"value":"2730-5953","type":"print"},{"value":"2730-5961","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,2]]},"assertion":[{"value":"11 July 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 November 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 December 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The author states that there is no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}