How Human-Centered Explainable AI Interface Are Designed and Evaluated: A Systematic Survey

TL;DR

This systematic survey reviews 53 publications on human-centered explainable AI interfaces, highlighting current trends and future directions to improve user interaction, interpretability, and effectiveness of XAI systems.

Contribution

It is among the first systematic surveys analyzing design and evaluation trends in human-centered explainable AI interfaces.

Findings

Identifies key trends in EI design and evaluation.

Highlights gaps and challenges in current EI research.

Suggests promising directions for future EI development.

Abstract

Despite its technological breakthroughs, eXplainable Artificial Intelligence (XAI) research has limited success in producing the {\em effective explanations} needed by users. In order to improve XAI systems' usability, practical interpretability, and efficacy for real users, the emerging area of {\em Explainable Interfaces} (EIs) focuses on the user interface and user experience design aspects of XAI. This paper presents a systematic survey of 53 publications to identify current trends in human-XAI interaction and promising directions for EI design and development. This is among the first systematic survey of EI research.