Towards a Praxis for Intercultural Ethics in Explainable AI

TL;DR

This paper proposes an intercultural ethics framework for XAI to enhance understanding and usability across diverse cultural contexts, especially in low-resource regions of the Global South.

Contribution

It introduces the concept of intercultural ethics in XAI, addressing cultural nuances and proposing approaches to make AI explanations more inclusive and effective.

Findings

Cultural differences significantly impact AI explainability adoption.

Integrating intercultural ethics can improve user understanding of AI.

New approaches are needed for culturally diverse AI explanation methods.

Abstract

Explainable AI (XAI) is often promoted with the idea of helping users understand how machine learning models function and produce predictions. Still, most of these benefits are reserved for those with specialized domain knowledge, such as machine learning developers. Recent research has argued that making AI explainable can be a viable way of making AI more useful in real-world contexts, especially within low-resource domains in the Global South. While AI has transcended borders, a limited amount of work focuses on democratizing the concept of explainable AI to the "majority world", leaving much room to explore and develop new approaches within this space that cater to the distinct needs of users within culturally and socially-diverse regions. This article introduces the concept of an intercultural ethics approach to AI explainability. It examines how cultural nuances impact the adoption and use of technology, the factors that impede how technical concepts such as AI are explained, and how integrating an intercultural ethics approach in the development of XAI can improve user understanding and facilitate efficient usage of these methods.