AI Explainability 360: Impact and Design
It addresses the need for explainable AI across stakeholders like citizens, regulators, and developers, though it is incremental as it builds on existing methods.
The paper examines the impact of AI Explainability 360, an open-source toolkit with ten explainability methods and two evaluation metrics, highlighting its adoption by the LF AI & Data Foundation and improvements in multiple metrics through case studies and community feedback.
As artificial intelligence and machine learning algorithms become increasingly prevalent in society, multiple stakeholders are calling for these algorithms to provide explanations. At the same time, these stakeholders, whether they be affected citizens, government regulators, domain experts, or system developers, have different explanation needs. To address these needs, in 2019, we created AI Explainability 360 (Arya et al. 2020), an open source software toolkit featuring ten diverse and state-of-the-art explainability methods and two evaluation metrics. This paper examines the impact of the toolkit with several case studies, statistics, and community feedback. The different ways in which users have experienced AI Explainability 360 have resulted in multiple types of impact and improvements in multiple metrics, highlighted by the adoption of the toolkit by the independent LF AI & Data Foundation. The paper also describes the flexible design of the toolkit, examples of its use, and the significant educational material and documentation available to its users.