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 2306.00380cs.AIcs.CY
收藏

可信人工智能综述:人工智能的元决策

Survey of Trustworthy AI: A Meta Decision of AI

University of Luxembourg(卢森堡大学);Monash University(莫纳什大学)

Caesar Wu, Yuan-Fang Lib, Pascal Bouvry

AI总结:

针对战略决策中AI信任的元决策问题,提出包含清晰表达、真实、基础三大领域及十个衡量维度的可信人工智能(TAI)新分类框架,拟以此从战略决策视角开展TAI全面综述。

摘要:

在制定战略决策时,我们常需要处理海量信息。当部分证据相互矛盾或存在悖论时,情况会更加复杂。此时的挑战在于如何判断哪些信息有用、哪些应当剔除,这一过程被称为元决策。同理,在将人工智能(AI)系统用于战略决策时,鉴于许多AI系统被视为处理海量数据的不透明“黑箱”,对AI本身的信任就成了一种元决策。信任一个不透明系统需要确定可信人工智能(TAI)的等级。我们提出了一种解决该问题的新方法,引入了一种全新的TAI分类体系或框架,它包含三个核心领域:清晰表达型、真实型和基础型,分别对应不同的信任等级。为支撑这些领域,我们构建了十个衡量信任的维度:可解释性/透明度、公平性/多样性、泛化性、隐私性、数据治理、安全性/鲁棒性、问责性、可复现性、可靠性和可持续性。我们旨在利用该分类体系开展全面综述,从战略决策视角探索不同的TAI方法。

英文摘要:

When making strategic decisions, we are often confronted with overwhelming information to process. The situation can be further complicated when some pieces of evidence are contradicted each other or paradoxical. The challenge then becomes how to determine which information is useful and which ones should be eliminated. This process is known as meta-decision. Likewise, when it comes to using Artificial Intelligence (AI) systems for strategic decision-making, placing trust in the AI itself becomes a meta-decision, given that many AI systems are viewed as opaque "black boxes" that process large amounts of data. Trusting an opaque system involves deciding on the level of Trustworthy AI (TAI). We propose a new approach to address this issue by introducing a novel taxonomy or framework of TAI, which encompasses three crucial domains: articulate, authentic, and basic for different levels of trust. To underpin these domains, we create ten dimensions to measure trust: explainability/transparency, fairness/diversity, generalizability, privacy, data governance, safety/robustness, accountability, reproducibility, reliability, and sustainability. We aim to use this taxonomy to conduct a comprehensive survey and explore different TAI approaches from a strategic decision-making perspective.

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。

↑