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 2307.00660cs.AIcs.CY
收藏

人工道德智能体的最低可解释性水平

Minimum Levels of Interpretability for Artificial Moral Agents

Imperial College London(伦敦帝国学院)

Avish Vijayaraghavan, Cosmin Badea

AI总结:

本文针对人工道德智能体(AMA)的安全部署问题,引入最低可解释性水平(MLI)概念,概述AI可解释性子领域并为各类智能体推荐相应MLI,以促进其有效使用、错误纠正及安全部署。

摘要:

随着人工智能(AI)模型规模不断扩大,其能力日益增强并逐渐融入各类决策系统。对于参与道德决策的模型,即人工道德智能体(AMA),可解释性提供了一种信任和理解智能体内部推理机制的途径,以便有效使用和纠正错误。本文概述了这一快速发展的AI可解释性子领域,引入了最低可解释性水平(MLI)概念,并为各类智能体推荐了相应的MLI,以助力其在真实环境中的安全部署。

英文摘要:

As artificial intelligence (AI) models continue to scale up, they are becoming more capable and integrated into various forms of decision-making systems. For models involved in moral decision-making, also known as artificial moral agents (AMA), interpretability provides a way to trust and understand the agent's internal reasoning mechanisms for effective use and error correction. In this paper, we provide an overview of this rapidly-evolving sub-field of AI interpretability, introduce the concept of the Minimum Level of Interpretability (MLI) and recommend an MLI for various types of agents, to aid their safe deployment in real-world settings.

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。

↑