Questioning the AI: Informing Design Practices for Explainable AI User Experiences

要旨

A surge of interest in explainable AI (XAI) has led to a vast collection of algorithmic work on the topic. While many recognize the necessity to incorporate explainability features in AI systems, how to address real-world user needs for understanding AI remains an open question. By interviewing 20 UX and design practitioners working on various AI products, we seek to identify gaps between the current XAI algorithmic work and practices to create explainable AI products. To do so, we develop an algorithm-informed XAI question bank in which user needs for explainability are represented as prototypical questions users might ask about the AI, and use it as a study probe. Our work contributes insights into the design space of XAI, informs efforts to support design practices in this space, and identifies opportunities for future XAI work. We also provide an extended XAI question bank and discuss how it can be used for creating user-centered XAI.

受賞
Honorable Mention
キーワード
Explainable AI
human-AI interaction
User experience
著者
Q. Vera Liao
IBM Research AI, Yorktown Heights, NY, USA
Daniel Gruen
IBM Research, Cambridge, MA, USA
Sarah Miller
IBM Research, Cambridge, MA, USA
DOI

10.1145/3313831.3376590

論文URL

https://doi.org/10.1145/3313831.3376590

会議: CHI 2020

The ACM CHI Conference on Human Factors in Computing Systems (https://chi2020.acm.org/)

セッション: AI/ML & seeing through the black box

Paper session
313C O'AHU
5 件の発表
2020-04-29 20:00:00
2020-04-29 21:15:00
日本語まとめ
読み込み中…