As artificial intelligence (AI) models continue to scale up, they are becoming more capable and integrated into various forms of decision-making systems. For models involved in moral decision-making, also known as artificial moral agents (AMA), interpretability provides a way to trust and understand the agent's internal reasoning mechanisms for effective use and error correction. In this paper, we provide an overview of this rapidly-evolving sub-field of AI interpretability, introduce the concept of the Minimum Level of Interpretability (MLI) and recommend an MLI for various types of agents, to aid their safe deployment in real-world settings.
Toward equipping Artificial Moral Agents with multiple ethical theories
Computer Science Department, University of Cape Town(开普敦大学计算机科学系);University of Cape Town(开普敦大学)
人工道德代理(Artificial Moral Agents,AMA)是计算机科学中的一个领域,其目的是创建能够做出类似于人类行为的道德决策的自主机器。研究人员提出了创造这种机器的理论方法,而哲学家则对这些机器应该如何运作,或者它们是否应该存在进行了争论。在目前理论化的AMA中,所有的研究和设计都是在没有或至多有一个特定的规范伦理理论作为基础的情况下完成的。这是有问题的,因为它缩小了AMA的功能能力和多功能性,这反过来又导致了少数人同意的道德结果(从而破坏了AMA在人类意义上的道德能力)。作为解决方案,我们设计了一个三层模型的一般规范的道德理论,可用于序列化的人和企业的道德观点的AMA在推理过程中使用。四个具体的道德规范(康德主义,神的命令理论,功利主义和利己主义)进行了建模和评估的概念证明规范建模。此外,所有模型都被序列化为XML/XSD,作为支持计算机化的证明。
Explaining Intrinsic Moral Self-Correction with Mechanistic Interpretability
Graduate Institute of Communication Engineering, National Taiwan University, Taipei, Taiwan(通讯工程研究院,国立台湾大学);MediaTek Research, Taipei, Taiwan(联发科研究,台北,台湾);Department of Electrical Engineering, National Taiwan University, Taipei, Taiwan(电气工程系,国立台湾大学);Department of Electrical Engineering, National Tsing Hua University, Hsinchu, Taiwan(电气工程系,国立清华大学);AI Research Center (AINTU), National Taiwan University, Taipei, Taiwan(人工智能研究中心(AINTU),国立台湾大学)
Analysing Moral Bias in Finetuned LLMs through Mechanistic Interpretability
Department of Computer Science and Engineering, University of Bologna, Bologna, Italy(计算机科学与工程系,博洛尼亚大学,意大利博洛尼亚);Center for Studies and Research in Cognitive Neuroscience, Department of Psychology, University of Bologna, Cesena, Italy(认知神经科学研究中心,心理学系,博洛尼亚大学,意大利塞森纳)
Artificial intelligence moral agent as Adam Smith's impartial spectator
Institute of Materials Research and Engineering, A*STAR (Agency for Science, Technology and Research)(材料研究与工程研究院,新加坡科技研究局);Center on AI Technology for Humankind (AiTH), NUS Business School, National University of Singapore(新加坡国立大学商学院人类人工智能技术中心(AiTH))
Ethical Considerations in Artificial Intelligence Courses
University of Kentucky(肯塔基大学);University of Southern California(南加州大学);University of Michigan(密歇根大学);IBM T.J. Watson Research Center(IBM T.J. 沃森研究中心);UNSW(新南威尔士大学);Data61/CSIRO(澳大利亚联邦科学与工业研究组织 Data61);TU Berlin(柏林工业大学)
Staying with the Uncertainty: Uncertainty-Scaffolding Strategies for Artificial Moral Advisors in LLM-to-LLM Simulated Conversations
Centre for Data Futures, The Dickson Poon School of Law, King’s College London(数据未来中心、迪克森·普恩法学院、伦敦国王学院);Department of Informatics, King’s College London(信息学院、伦敦国王学院);LangAI, Center for Language AI Research, Tohoku University(LangAI、语言人工智能研究中心、东北大学);Neukom Institute for Computational Science, Dartmouth College(计算科学尼科姆研究所、达特茅斯学院)
University of Tübingen, Carl Friedrich von Weizsäcker Center(图宾根大学,卡尔·弗里德里希·冯·魏茨泽克中心);University of Geneva, Department of Philosophy(日内瓦大学哲学系);University of Zurich, Department of Philosophy(苏黎世大学哲学系)
Human Perceptions on Moral Responsibility of AI: A Case Study in AI-Assisted Bail Decision-Making
KAIST(韩国科学技术院);IBS(韩国基础科学研究院);Max Planck Institute for Software Systems(马克斯·普朗克软件系统研究所);Max Planck Institute for Research on Collective Goods(马克斯·普朗克集体利益研究所)
Do Consumers Accept AIs as Moral Compliance Agents?
Faculty of Business and Economics, University of Melbourne(商学院与经济学院,墨尔本大学);University of Melbourne(墨尔本大学);University of Melbourne, Parkville(墨尔本大学,帕克维尔)
Culturally-Attuned Moral Machines: Implicit Learning of Human Value Systems by AI through Inverse Reinforcement Learning
Paul G. Allen School of Computer Science and Engineering, University of Washington(保罗·G·阿伦计算机科学与工程学院,华盛顿大学);Institute for Learning and Brain Sciences, University of Washington(学习与脑科学研究所,华盛顿大学)
The AI Double Standard: Humans Judge All AIs for the Actions of One
Sentience Institute(感知研究所);Max Planck institute for Human Cognitive and Brain Sciences(马克斯·普朗克人类认知与脑科学研究所);Stanford University(斯坦福大学);University of Chicago(芝加哥大学)
Forward College(前进学院);University of Illinois at Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校);University of Nebraska, Lincoln(内布拉斯加大学林肯分校);Technische Universität Berlin(柏林技术大学);Humboldt Institute for Internet and Society(洪堡互联网与社会研究所);Stony Brook University(石溪大学)
Social Catalysts, Not Moral Agents: The Illusion of Alignment in LLM Societies
Institute of Neuroscience, Chinese Academy of Sciences(中国科学院神经科学研究所);School of Philosophy, Anhui University(安徽大学哲学学院);Department of Psychology and Behavioral Sciences, Zhejiang University(浙江大学心理学与行为科学系);Mental Health Education Center, North China Electric Power University(华北电力大学心理健康教育中心)
Algorithmic Fairness in AI Surrogates for End-of-Life Decision-Making
The Department of Computing & Software Systems University of Washington Bothell Harborview Medical Center, UW Medicine(计算与软件系统系华盛顿大学Bothell分校哈佛湾医疗中心,华盛顿大学医学部)
针对临终决策 AI 替代者,本文将主要公平概念映射到现实临终场景并跨道德传统考察,提出公平应包含道德代表性及对患者价值观、关系与世界观的忠实。
Multilevel Interpretability Of Artificial Neural Networks: Leveraging Framework And Methods From Neuroscience
University of Cambridge(剑桥大学);University of Oxford(牛津大学);Imperial College London(帝国理工学院);Massachusetts Institute of Technology(麻省理工学院);Georgia Institute of Technology(佐治亚理工学院);New York University(纽约大学);Princeton University(普林斯顿大学)
Autonomy, Social Norms, and Alignment: Towards a Developmental Framework for Autonomous Artificial Agents
Institute of Cognitive Sciences and Technologies (ISTC-CNR)(认知科学与技术研究所(ISTC-CNR));Interdepartmental Center for Research Ethics and Integrity (CID Ethics)(跨部门研究伦理与诚信中心(CID Ethics))