Large-scale behavioral datasets enable researchers to use complex machine learning algorithms to better predict human behavior, yet this increased predictive power does not always lead to a better understanding of the behavior in question. In this paper, we outline a data-driven, iterative procedure that allows cognitive scientists to use machine learning to generate models that are both interpretable and accurate. We demonstrate this method in the domain of moral decision-making, where standard experimental approaches often identify relevant principles that influence human judgments, but fail to generalize these findings to "real world" situations that place these principles in conflict. The recently released Moral Machine dataset allows us to build a powerful model that can predict the outcomes of these conflicts while remaining simple enough to explain the basis behind human decisions.
When to Make Exceptions: Exploring Language Models as Accounts of Human Moral Judgment
MPI(马克斯·普朗克研究所);ETH Zürich(苏黎世联邦理工学院);MIT(麻省理工学院);Harvard(哈佛大学);IIT Kharagpur(印度理工学院卡拉格普尔分校);Carnegie Mellon University(卡内基梅隆大学);University of Michigan(密歇根大学);MPI for Intelligent Systems(马克斯·普朗克智能系统研究所)
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)
Judge Business School, University of Cambridge(剑桥大学贾奇商学院);Institute of Metabolic Science, School of Clinical Medicine, University of Cambridge(剑桥大学临床医学院代谢科学研究所);School of Business, University of Queensland(昆士兰大学商学院)
When Ethics and Payoffs Diverge: LLM Agents in Morally Charged Social Dilemmas
ETH Zürich(苏黎世联邦理工学院);University of Zurich(苏黎世大学);Carnegie Mellon University(卡内基梅隆大学);University of Michigan(密歇根大学);Max Planck Institute for Intelligent Systems, Tübingen(图宾根人工智能研究所);University of Toronto(多伦多大学);Vector Institute(向量研究所)
That's All Folks: a KG of Values as Commonsense Social Norms and Behaviors
University of Bologna(博洛尼亚大学);ISTC - CNR(意大利国家研究委员会认知科学与技术研究所)
价值观,正如在伦理学中所预期的那样,决定了道德和社会规范的形式和有效性,使我们的日常个人和社区行为建立在常识知识的基础上。将人类互动中潜在的道德内容形式化是一个有吸引力的观点,可以更深入地理解社会动态和个人认知和行为维度。为了解决这个问题,一些理论框架提供了不同的价值模型,并将它们组织成不同的分类。最常用的理论的问题是,他们采取了文化独立的角度,而许多实体被认为是“价值”是基于常识知识和表达在日常生活中的互动。我们在这里提出了两个本体论模块,FOLK,一个用于广义价值观的本体论,和That's All Folks,一个用于词汇和事实民间价值触发器的模块,其目的是补充主要理论,提供一种方法来识别主要价值理论没有考虑到的价值观,但仍然在日常人类互动中发挥关键作用,并塑造社会结构,文化偏见和个人信仰。通过使用基于框架的方法从文本中自动检测值来测试资源。