Combining Human-centred Explainability and Explainable AI

TL;DR

This paper explores the distinctions and potential integration of human-centered explainability and explainable AI, proposing a new algebraic machine learning approach as an initial step towards combining these perspectives.

Contribution

It introduces the concept of integrating human-centered explainability with xAI and presents preliminary algebraic machine learning work as an example.

Findings

Identified key differences between HCx and xAI

Proposed a new algebraic approach for combined explainability

Encouraged community discussion on design opportunities

Abstract

This position paper looks at differences between the current understandings of human-centered explainability and explainability AI. We discuss current ideas in both fields, as well as the differences and opportunities we discovered. As an example of combining both, we will present preliminary work on a new algebraic machine learning approach. We are excited to continue discussing design opportunities for human-centered explainability (HCx) and xAI with the broader HCxAI community.