A New Perspective on Evaluation Methods for Explainable Artificial Intelligence (XAI)

TL;DR

This paper critically examines the perceived trade-off between explainability and performance in XAI, proposing a nuanced approach that considers resources, domain specifics, and risk to improve evaluation methods.

Contribution

It introduces a nuanced perspective on evaluating XAI, challenging the traditional trade-off assumption and providing a foundation for future research and best practices in Requirements Engineering.

Findings

Trade-off between explainability and performance is not absolute.

Resource availability influences the prioritization of explainability.

A nuanced approach can better balance system quality aspects.

Abstract

Within the field of Requirements Engineering (RE), the increasing significance of Explainable Artificial Intelligence (XAI) in aligning AI-supported systems with user needs, societal expectations, and regulatory standards has garnered recognition. In general, explainability has emerged as an important non-functional requirement that impacts system quality. However, the supposed trade-off between explainability and performance challenges the presumed positive influence of explainability. If meeting the requirement of explainability entails a reduction in system performance, then careful consideration must be given to which of these quality aspects takes precedence and how to compromise between them. In this paper, we critically examine the alleged trade-off. We argue that it is best approached in a nuanced way that incorporates resource availability, domain characteristics, and considerations of risk. By providing a foundation for future research and best practices, this work aims to advance the field of RE for AI.