AI ethics is an emerging field with multiple, competing narratives about how to best solve the problem of building human values into machines. Two major approaches are focused on bias and compliance, respectively. But neither of these ideas fully encompasses ethics: using moral principles to decide how to act in a particular situation. Our method posits that the way data is labeled plays an essential role in the way AI behaves, and therefore in the ethics of machines themselves. The argument combines a fundamental insight from ethics (i.e. that ethics is about values) with our practical experience building and scaling machine learning systems. We want to build AI that is actually ethical by first addressing foundational concerns: how to build good systems, how to define what is good in relation to system architecture, and who should provide that definition.
Building ethical AI creates a foundation of trust between a company and the users of that platform. But this trust is unjustified unless users experience the direct value of ethical AI. Until users have real control over how algorithms behave, something is missing in current AI solutions. This causes massive distrust in AI, and apathy towards AI ethics solutions. The scope of this paper is to propose an alternative path that allows for the plurality of values and the freedom of individual expression. Both are essential for realizing true moral character.
Breaking Up with Normatively Monolithic Agency with GRACE: A Reason-Based Neuro-Symbolic Architecture for Safe and Ethical AI Alignment
German Research Center for Artificial Intelligence（德国人工智能研究中心）；Center for European Research in Trusted AI (CERTAIN)（可信AI欧洲研究中心）；Saarland Informatics Campus（萨尔州信息学校区）；Computer Science Department, TU Darmstadt（图宾根大学计算机科学系）
Institut Polytechnique de Paris（巴黎理工学院）；Télécom Paris（巴黎电信学院）；Minsait by Indra Sistemas SA（英德拉系统公司旗下Minsait公司）；Centro Singular de Investigación en Tecnoloxías Intelixentes (CiTIUS)（智能技术卓越研究中心（CiTIUS））；Universidade de Santiago de Compostela（圣地亚哥德孔波斯特拉大学）
