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 2401.08672cs.LGcs.AIq-bio.NC
收藏

概念对齐

Concept Alignment

Princeton University(普林斯顿大学);University of California Merced(加州大学默塞德分校)

Sunayana Rane, Polyphony J. Bruna, Ilia Sucholutsky, Christopher Kello, Thomas L. Griffiths

AI总结:

本文提出在价值对齐之前必须先实现人类与AI系统之间的概念对齐,通过整合哲学、认知科学与深度学习视角,分析概念学习现状并指出利用现有工具加速概念对齐的路径。

摘要:

关于AI对齐(人类与AI系统之间的对齐)的讨论一直聚焦于价值对齐,广义上指创建共享人类价值观的AI系统。我们认为,在我们甚至尝试对齐价值之前,AI系统与人类必须对齐它们用来理解世界的概念,这一点至关重要。我们整合来自哲学、认知科学和深度学习的观点,以解释人类与机器之间不仅需要价值对齐,还需要概念对齐的原因。我们总结了关于人类和机器当前如何学习概念的现有论述,并概述了在走向共享概念道路上的机遇与挑战。最后,我们解释了如何利用认知科学和AI研究中已经开发出来的工具来加速概念对齐的进展。

英文摘要:

Discussion of AI alignment (alignment between humans and AI systems) has focused on value alignment, broadly referring to creating AI systems that share human values. We argue that before we can even attempt to align values, it is imperative that AI systems and humans align the concepts they use to understand the world. We integrate ideas from philosophy, cognitive science, and deep learning to explain the need for concept alignment, not just value alignment, between humans and machines. We summarize existing accounts of how humans and machines currently learn concepts, and we outline opportunities and challenges in the path towards shared concepts. Finally, we explain how we can leverage the tools already being developed in cognitive science and AI research to accelerate progress towards concept alignment.

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。

↑