arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2412.19010cs.AI
收藏

一种适用性理论及其在生成式人工智能中的应用

A theory of appropriateness with applications to generative artificial intelligence

Google DeepMind(谷歌DeepMind);Mila - Québec AI Institute(米拉-魁北克人工智能研究所);University of Toronto(多伦多大学);Max Planck Institute for Human Development(马克斯·普朗克人类发展研究所)
Joel Z. Leibo, Alexander Sasha Vezhnevets, Manfred Diaz, John P. Agapiou, William A. Cunningham, Peter Sunehag, Julia Haas, Raphael Koster, Edgar A. Duéñez-Guzm… 展开作者

Joel Z. Leibo, Alexander Sasha Vezhnevets, Manfred Diaz, John P. Agapiou, William A. Cunningham, Peter Sunehag, Julia Haas, Raphael Koster, Edgar A. Duéñez-Guzmán, William S. Isaac, Georgios Piliouras, Stanley M. Bileschi, Iyad Rahwan, Simon Osindero

AI总结:

本文提出一种适用性理论,分析其如何引导人类决策并可能在大脑中实现,进而为负责任地部署生成式人工智能提供评估与改进依据。

摘要:

什么是适用性?人类在多种尺度上穿梭于相互交织的、关于不同情境下何为适当的概念拼图之中。我们与朋友相处时是一种行为方式,与家人相处时是另一种,而在办公室中又是另一种。对于人工智能而言,同样如此:喜剧写作助手所应具备的适当行为,与客户服务代表所应具备的适当行为并不相同。是什么决定了哪些行为在哪些情境中是适当的?又是什么导致这些标准随时间而变化?由于所有关于人工智能适用性的判断最终都由人类作出,我们需要理解适用性如何引导人类决策,以便恰当地评估人工智能决策并加以改进。本文提出一种适用性理论:它如何在人类社会中发挥作用,如何可能在大脑中实现,以及它对负责任地部署生成式人工智能技术意味着什么。

英文摘要:

What is appropriateness? Humans navigate a multi-scale mosaic of interlocking notions of what is appropriate for different situations. We act one way with our friends, another with our family, and yet another in the office. Likewise for AI, appropriate behavior for a comedy-writing assistant is not the same as appropriate behavior for a customer-service representative. What determines which actions are appropriate in which contexts? And what causes these standards to change over time? Since all judgments of AI appropriateness are ultimately made by humans, we need to understand how appropriateness guides human decision making in order to properly evaluate AI decision making and improve it. This paper presents a theory of appropriateness: how it functions in human society, how it may be implemented in the brain, and what it means for responsible deployment of generative AI technology.

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。

↑