arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2410.21183cs.HC
收藏

迈向以人为本的可解释人工智能(XAI)设计:实证研究综述

Towards Human-centered Design of Explainable Artificial Intelligence (XAI): A Survey of Empirical Studies

Shuai Ma

AI总结:

本文综述以人为本的XAI实证研究,梳理算法、利益相关者、需求发现、设计空间、评估指标、发现与陷阱,并提出结合实证研究的设计框架。

摘要:

随着人工智能研究的进展,AI已越来越多地被应用于众多领域,从电影推荐等低风险日常任务,到医学和刑事司法决策等高风险任务。可解释性正成为人们理解、信任并采用AI应用的一项基本要求。尽管AI研究界已经产生了大量可解释人工智能(XAI)算法,但在真实世界AI应用中,XAI的成功案例仍然相对稀少。这可能源于XAI的设计目标与终端用户实际感知XAI的方式之间存在差距。由于可解释性本质上是一种以人为本的属性,近年来,XAI领域开始接纳以人为本的方法,并日益认识到通过让人类受试者参与来对XAI设计开展实证研究的重要性。为了朝着系统综述以人为本的XAI设计实证研究迈进一步,在本综述中,我们首先简要介绍现有实证研究中常用XAI算法的技术图景。随后,我们分析多元利益相关者和需求发现方法。接着,我们概述当前以人为本的XAI设计中所探索的设计空间。此外,我们基于评估目标总结评估指标。之后,我们分析从现有研究中得出的共同发现和陷阱。对于每一章,我们都总结当前挑战与研究机会。最后,我们以一个结合实证研究的以人为本XAI设计框架结束本综述。

英文摘要:

With the advances of AI research, AI has been increasingly adopted in numerous domains, ranging from low-stakes daily tasks such as movie recommendations to high-stakes tasks such as medicine, and criminal justice decision-making. Explainability is becoming an essential requirement for people to understand, trust and adopt AI applications. Despite a vast collection of explainable AI (XAI) algorithms produced by the AI research community, successful examples of XAI are still relatively scarce in real-world AI applications. This can be due to the gap between what the XAI is designed for and how the XAI is actually perceived by end-users. As explainability is an inherently human-centered property, in recent years, the XAI field is starting to embrace human-centered approaches and increasingly realizing the importance of empirical studies of XAI design by involving human subjects. To move a step towards a systematic review of empirical study for human-centered XAI design, in this survey, we first brief the technical landscape of commonly used XAI algorithms in existing empirical studies. Then we analyze the diverse stakeholders and needs-finding approaches. Next, we provide an overview of the design space explored in the current human-centered XAI design. Further, we summarize the evaluation metrics based on evaluation goals. Afterward, we analyze the common findings and pitfalls derived from existing studies. For each chapter, we provide a summary of current challenges and research opportunities. Finally, we conclude the survey with a framework for human-centered XAI design with empirical studies.

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。

↑