Human-Centered Explainable AI (HCXAI): Beyond Opening the Black-Box of AI

Explainability of AI systems is crucial to hold them accountable because they are increasingly becoming consequential in our lives by powering high-stakes decisions in domains like healthcare and law. When it comes to Explainable AI (XAI), understanding who interacts with the black-box of AI is just as important as “opening” it, if not more. Yet the discourse of XAI has been predominantly centered around the black-box, suffering from deficiencies in meeting user needs and exacerbating issues of algorithmic opacity. To address these issues, researchers have called for human-centered approaches to XAI. In this second CHI workshop on Human-centered XAI (HCXAI), we build on the success of the first installment from CHI 2021 to expand the conversation around XAI. We chart the domain and shape the HCXAI discourse with reflective discussions from diverse stakeholders. The goal of the second installment is to go beyond the black box and 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.

[1]  Mohan S. Kankanhalli,et al.  Trends and Trajectories for Explainable, Accountable and Intelligible Systems: An HCI Research Agenda , 2018, CHI.

[2]  Mark O. Riedl,et al.  Human-centered Explainable AI: Towards a Reflective Sociotechnical Approach , 2020, HCI.

[3]  Philipp Wintersberger,et al.  Operationalizing Human-Centered Perspectives in Explainable AI , 2021, CHI Extended Abstracts.

[4]  R. Bellamy,et al.  Explainable Active Learning (XAL): Toward AI Explanations as Interfaces for Machine Teachers , 2021 .

[5]  Mark R. Lehto,et al.  Foundations for an Empirically Determined Scale of Trust in Automated Systems , 2000 .

[6]  Rachel K. E. Bellamy,et al.  Explaining models an empirical study of how explanations impact fairness judgment , 2019 .

[7]  Yunfeng Zhang,et al.  Effect of confidence and explanation on accuracy and trust calibration in AI-assisted decision making , 2020, FAT*.

[8]  Cynthia Rudin,et al.  The age of secrecy and unfairness in recidivism prediction , 2018, 2.1.

[9]  Daniel S. Weld,et al.  No Explainability without Accountability: An Empirical Study of Explanations and Feedback in Interactive ML , 2020, CHI.

[10]  M. C. Elish,et al.  A Study of Integrating AI in Clinical Care , 2020 .

[11]  Eric D. Ragan,et al.  A Multidisciplinary Survey and Framework for Design and Evaluation of Explainable AI Systems , 2018, ACM Trans. Interact. Intell. Syst..

[12]  Q. Liao,et al.  Questioning the AI: Informing Design Practices for Explainable AI User Experiences , 2020, CHI.

[13]  R. Westrum.  The Social Construction of Technological Systems , 1989 .

[14]  Johanna D. Moore,et al.  Explanation in Expert Systemss: A Survey , 1988 .

[15]  Holger Hermanns,et al.  What Do We Want From Explainable Artificial Intelligence (XAI)? - A Stakeholder Perspective on XAI and a Conceptual Model Guiding Interdisciplinary XAI Research , 2021, Artif. Intell..

[16]  Alejandro Barredo Arrieta,et al.  Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI , 2019, Inf. Fusion.

[17]  D. MacKenzie.  Material Signals: A Historical Sociology of High-Frequency Trading1 , 2018, American Journal of Sociology.

[18]  Mark O. Riedl,et al.  The Who in Explainable AI: How AI Background Shapes Perceptions of AI Explanations , 2021, ArXiv.

[19]  Gary Klein,et al.  Metrics for Explainable AI: Challenges and Prospects , 2018, ArXiv.

[20]  Christian Biemann,et al.  What do we need to build explainable AI systems for the medical domain? , 2017, ArXiv.

[21]  Mark O. Riedl,et al.  Expanding Explainability: Towards Social Transparency in AI systems , 2021, CHI.

[22]  Bruce N. Walker,et al.  Situational Trust Scale for Automated Driving (STS-AD): Development and Initial Validation , 2020, AutomotiveUI.

[23]  Zachary Chase Lipton.  The mythos of model interpretability , 2016, ACM Queue.

[24]  Tim Miller,et al.  Explanation in Artificial Intelligence: Insights from the Social Sciences , 2017, Artif. Intell..

[25]  Mark O. Riedl,et al.  Automated rationale generation: a technique for explainable AI and its effects on human perceptions , 2019, IUI.

[26]  M. Kaminski.  The right to explanation, explained , 2018, Research Handbook on Information Law and Governance.

[27]  Franco Turini,et al.  A Survey of Methods for Explaining Black Box Models , 2018, ACM Comput. Surv..