Modeling and Reasoning with Preferences and Ethical Priorities in AI Systems
Modeling and Reasoning with Preferences and Ethical Priorities in AI Systems
复制标题
人工智能系统中具有偏好和道德优先级的建模和推理
DOI：
10.1093/oso/9780190905033.003.0005
复制
发表时间：
2020
影响因子：
4.1
通讯作者：
K. Venable
中科院分区：
文献类型：
--
作者：
Andrea Loreggia;Nicholas Mattei;F. Rossi;K. Venable
当人工智能系统做出影响我们生活的决定时，我们必须确保这些系统按照人类所遵循的相同约束、指导方针和道德原则运行。人类做出许多复杂的决定依赖于他们的主观偏好，但他们的决定通常也受到这些道德优先事项的约束。因此，为人工智能系统配备工具来评估偏好是否与其他优先事项兼容是至关重要的。在计算机科学中，条件偏好网络（CP-nets）以图形方式表示条件和定性偏好关系，可用于建模、联合收割机和比较主观偏好和伦理优先级。本章提出，可以使用CP网来衡量代理的主观偏好和代理社区的道德原则之间的距离，以确保AI系统的决策与给定的一组道德优先级保持一致。
As AI systems make decisions that affect our lives, we must ensure that these systems operate according to the same constraints, guidelines, and ethical principles that a human would follow. Humans make many complex decisions that rely on their subjective preferences, but their decisions are usually also constrained by these ethical priorities. Hence it is essential to equip AI systems with the tools to evaluate whether or not preferences are compatible with these other priorities. In computer science, the Conditional Preference networks (CP-nets), which graphically represent conditional and qualitative preference relations, can be used to model, combine, and compare subjective preferences and ethical priorities. This chapter proposes that one can use CP-nets to measure the distance between an agent’s subjective preference and the ethical principles of the agent’s community in order to ensure that the decisions of an AI system are aligned with a given set of ethical priorities.