arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2305.02748cs.AIcs.CYcs.MA
收藏

人类价值观的计算框架

A computational framework for human values

Artificial Intelligence Research Institute (IIIA-CSIC)(人工智能研究 institute (IIIA-CSIC))

Nardine Osman, Mark d'Inverno

AI总结:

本文提出一个基于社会科学的正式框架,用于系统研究如何通过人类价值观设计伦理人工智能。

摘要:

在心理学、哲学和社会科学对人类价值观本质的研究中,存在一个明确的共识,即价值观指导行为。最近,一种认识逐渐形成,即价值观为工程伦理人工智能提供了一种手段。事实上,斯图尔特·拉塞尔提出了将人工智能的关注点从单纯的“智能”转向“能够证明与人类价值观一致的智能”的主张。这一挑战——价值对齐问题——以及其他包括人工智能学习人类价值观、将个体价值观聚合为群体、以及设计计算机制来推理价值观的问题,已经激发了持续的研究努力。尽管如此,至今仍未提出正式的、计算定义的价值观。我们通过一个扎根于社会科学的正式概念框架来解决这一问题,为系统、整合和跨学科研究如何利用人类价值观来设计伦理人工智能提供基础。

英文摘要:

In the diverse array of work investigating the nature of human values from psychology, philosophy and social sciences, there is a clear consensus that values guide behaviour. More recently, a recognition that values provide a means to engineer ethical AI has emerged. Indeed, Stuart Russell proposed shifting AI's focus away from simply ``intelligence'' towards intelligence ``provably aligned with human values''. This challenge -- the value alignment problem -- with others including an AI's learning of human values, aggregating individual values to groups, and designing computational mechanisms to reason over values, has energised a sustained research effort. Despite this, no formal, computational definition of values has yet been proposed. We address this through a formal conceptual framework rooted in the social sciences, that provides a foundation for the systematic, integrated and interdisciplinary investigation into how human values can support designing ethical AI.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑