The dominant practice of AI alignment assumes (1) that preferences are an adequate representation of human values, (2) that human rationality can be understood in terms of maximizing the satisfaction of preferences, and (3) that AI systems should be aligned with the preferences of one or more humans to ensure that they behave safely and in accordance with our values. Whether implicitly followed or explicitly endorsed, these commitments constitute what we term a preferentist approach to AI alignment. In this paper, we characterize and challenge the preferentist approach, describing conceptual and technical alternatives that are ripe for further research. We first survey the limits of rational choice theory as a descriptive model, explaining how preferences fail to capture the thick semantic content of human values, and how utility representations neglect the possible incommensurability of those values. We then critique the normativity of expected utility theory (EUT) for humans and AI, drawing upon arguments showing how rational agents need not comply with EUT, while highlighting how EUT is silent on which preferences are normatively acceptable. Finally, we argue that these limitations motivate a reframing of the targets of AI alignment: Instead of alignment with the preferences of a human user, developer, or humanity-writ-large, AI systems should be aligned with normative standards appropriate to their social roles, such as the role of a general-purpose assistant. Furthermore, these standards should be negotiated and agreed upon by all relevant stakeholders. On this alternative conception of alignment, a multiplicity of AI systems will be able to serve diverse ends, aligned with normative standards that promote mutual benefit and limit harm despite our plural and divergent values.
Alignment Imprint: Zero-Shot AI-Generated Text Detection via Provable Preference Discrepancy
Nankai University(南开大学);Tsinghua University(清华大学);Harbin Institute of Technology, Shenzhen(哈尔滨工业大学(深圳));Peng Cheng Laboratory(鹏城实验室);Wuhan University(武汉大学)
Preference Orchestrator: Prompt-Aware Multi-Objective Alignment for Large Language Models
School of Computer Science and Engineering(计算机科学与工程学院);Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications(新一代人工智能技术及其交叉应用关键实验室);Ministry of Education(教育部)
Harvard University(哈佛大学);University of California Berkeley(加州大学伯克利分校);Massachusetts Institute of Technology(麻省理工学院);Ikigai Labs(Ikigai实验室);University of California San Diego(加州大学圣地亚哥分校)
Differentially Private Preference Data Synthesis for Large Language Model Alignment
Department of Computer Science, University of Virginia, Charlottesville, Virginia, USA(弗吉尼亚大学计算机科学系);Department of Electrical and Computer Engineering, University of Virginia, Charlottesville, Virginia, USA(弗吉尼亚大学电气与计算机工程系)
Adaptive Helpfulness-Harmlessness Alignment with Preference Vectors
National Taiwan University(国立台湾大学);Texas A&M University(德克萨斯A&M大学);Appier AI Research(Appier人工智能研究院);Graduate Institute of Communication Engineering, National Taiwan University(国立台湾大学通信工程研究所)
FlipGuard: Defending Preference Alignment against Update Regression with Constrained Optimization
University of Science and Technology of China(中国科学技术大学);State Key Laboratory of Communication Content Cognition(通信内容认知国家重点实验室);Beijing University of Posts and Telecommunications(北京邮电大学)
Free Lunch Alignment of Text-to-Image Diffusion Models without Preference Image Pairs
University of British Columbia(不列颠哥伦比亚大学);Vector Institute for AI(人工智能向量研究所);Canada CIFAR AI Chair(加拿大CIFAR人工智能主席);Kling Team, Kuaishou Technology(快手科技 Kling 团队);NSERC CRC Chair(加拿大NSERC CRC主席)
Gaoling School of Artificial Intelligence, Renmin University of China(中国人民大学高瓴人工智能学院);Department of Computer Science and Technology, Tsinghua University(清华大学计算机科学与技术系);Tencent Inc.(腾讯公司)