How to Evaluate Explainability? -- A Case for Three Criteria

TL;DR

This paper advocates for three key criteria—comprehensibility, fidelity, and assessability—to evaluate the explainability of software systems, emphasizing the need for consensus and appropriate methods in this emerging field.

Contribution

It introduces three core criteria for evaluating explainability, fostering discussion and development of suitable evaluation methods in the field.

Findings

Proposes three criteria for explainability evaluation

Highlights the lack of consensus on evaluation methods

Encourages multidisciplinary discussion on evaluation standards

Abstract

The increasing complexity of software systems and the influence of software-supported decisions in our society have sparked the need for software that is safe, reliable, and fair. Explainability has been identified as a means to achieve these qualities. It is recognized as an emerging non-functional requirement (NFR) that has a significant impact on system quality. However, in order to develop explainable systems, we need to understand when a system satisfies this NFR. To this end, appropriate evaluation methods are required. However, the field is crowded with evaluation methods, and there is no consensus on which are the "right" ones. Much less, there is not even agreement on which criteria should be evaluated. In this vision paper, we will provide a multidisciplinary motivation for three such quality criteria concerning the information that systems should provide: comprehensibility, fidelity, and assessability. Our aim is to to fuel the discussion regarding these criteria, such that adequate evaluation methods for them will be conceived.