Can Requirements Engineering Support Explainable Artificial Intelligence? Towards a User-Centric Approach for Explainability Requirements

TL;DR

This paper explores how requirements engineering can support the development of explainable AI systems by addressing challenges and proposing a framework for integrating explainability requirements into AI development processes.

Contribution

It introduces a novel framework and research directions for incorporating explainability requirements into requirements engineering practices for AI systems.

Findings

Identifies key challenges in XAI and RE integration

Proposes a framework to align RE practices with XAI needs

Suggests future research directions for user-centric explainability

Abstract

With the recent proliferation of artificial intelligence systems, there has been a surge in the demand for explainability of these systems. Explanations help to reduce system opacity, support transparency, and increase stakeholder trust. In this position paper, we discuss synergies between requirements engineering (RE) and Explainable AI (XAI). We highlight challenges in the field of XAI, and propose a framework and research directions on how RE practices can help to mitigate these challenges.