AI Explainability 360: Impact and Design

TL;DR

This paper discusses the development, impact, and design of AI Explainability 360, an open-source toolkit providing diverse explainability methods to meet various stakeholder needs in AI transparency.

Contribution

It introduces the AI Explainability 360 toolkit, details its impact through case studies and community feedback, and highlights its flexible design and educational resources.

Findings

Widespread adoption by the LF AI & Data Foundation

Positive impact on explanation quality and user understanding

Effective support for diverse stakeholder explanation needs

Abstract

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.