How to choose an Explainability Method? Towards a Methodical Implementation of XAI in Practice

TL;DR

This paper emphasizes the importance of selecting appropriate explainability methods in AI, proposing a methodology to align stakeholder needs with suitable XAI techniques to improve practical implementation.

Contribution

It introduces a methodology to systematically match stakeholder requirements with explanation methods, bridging the gap between technical solutions and user needs in XAI.

Findings

Development of characterization documents for XAI methods and user requirements

A proposed methodology to guide the selection of explainability techniques

Facilitates practical implementation of XAI in organizational contexts

Abstract

Explainability is becoming an important requirement for organizations that make use of automated decision-making due to regulatory initiatives and a shift in public awareness. Various and significantly different algorithmic methods to provide this explainability have been introduced in the field, but the existing literature in the machine learning community has paid little attention to the stakeholder whose needs are rather studied in the human-computer interface community. Therefore, organizations that want or need to provide this explainability are confronted with the selection of an appropriate method for their use case. In this paper, we argue there is a need for a methodology to bridge the gap between stakeholder needs and explanation methods. We present our ongoing work on creating this methodology to help data scientists in the process of providing explainability to stakeholders. In particular, our contributions include documents used to characterize XAI methods and user requirements (shown in Appendix), which our methodology builds upon.