Operationalizing Human-Centered Perspectives in Explainable AI
Operationalizing Human-Centered Perspectives in Explainable AI
复制标题
DOI：
10.1145/3411763.3441342
复制
发表时间：
2021-05
期刊：
影响因子：
--
通讯作者：
Upol Ehsan;Philipp Wintersberger;Q. Liao;Martina Mara;M. Streit;Sandra Wachter;A. Riener;Mark O. Riedl
中科院分区：
文献类型：
--
作者：
Upol Ehsan;Philipp Wintersberger;Q. Liao;Martina Mara;M. Streit;Sandra Wachter;A. Riener;Mark O. Riedl
人工智能（AI）对我们生活的影响是深远的——随着人工智能系统在医疗、金融、移动、法律等高风险领域的激增，这些系统必须能够全面地向不同的最终用户解释它们的决定。然而，可解释人工智能（XAI）的论述主要集中在以算法为中心的方法上，在满足用户需求方面存在差距，并加剧了算法不透明的问题。为了解决这些问题，研究人员呼吁采用以人为本的方法来研究XAI。有必要绘制领域图表，并通过来自不同利益相关者的反思讨论来塑造XAI的话语。本次研讨会的目标是研究如何在概念、方法和技术层面上实现XAI中以人为中心的透视图。鼓励整体（历史、社会学和技术）方法，我们强调“操作化”，旨在为XAI产生可操作的框架、可转移的评估方法、具体的设计指导方针，并阐明协调的研究议程。
The realm of Artificial Intelligence (AI)’s impact on our lives is far reaching – with AI systems proliferating high-stakes domains such as healthcare, finance, mobility, law, etc., these systems must be able to explain their decision to diverse end-users comprehensibly. Yet the discourse of Explainable AI (XAI) has been predominantly focused on algorithm-centered approaches, suffering from gaps in meeting user needs and exacerbating issues of algorithmic opacity. To address these issues, researchers have called for human-centered approaches to XAI. There is a need to chart the domain and shape the discourse of XAI with reflective discussions from diverse stakeholders. The goal of this workshop is to examine how human-centered perspectives in XAI can be operationalized at the conceptual, methodological, and technical levels. Encouraging holistic (historical, sociological, and technical) approaches, we put an emphasis on “operationalizing”, aiming to produce actionable frameworks, transferable evaluation methods, concrete design guidelines, and articulate a coordinated research agenda for XAI.