Explanation User Interfaces: A Systematic Literature Review

TL;DR

This paper systematically reviews Explanation User Interfaces (XUIs) in AI, highlighting design solutions and guidelines, and introduces HERMES, a platform to aid human-centered development and evaluation of explainable interfaces.

Contribution

It provides a comprehensive literature review of XUIs and introduces HERMES, a platform to support human-centered design and assessment of explainable AI interfaces.

Findings

Identifies key design guidelines for XUIs

Summarizes common solutions in XUI development

Provides a platform to facilitate XUI design and evaluation

Abstract

Artificial Intelligence (AI) is one of the major technological advancements of this century, bearing incredible potential for users through AI-powered applications and tools in numerous domains. Being often black-box (i.e., its decision-making process is unintelligible), developers typically resort to eXplainable Artificial Intelligence (XAI) techniques to interpret the behaviour of AI models to produce systems that are transparent, fair, reliable, and trustworthy. However, presenting explanations to the user is not trivial and is often left as a secondary aspect of the system's design process, leading to AI systems that are not useful to end-users. This paper presents a Systematic Literature Review on Explanation User Interfaces (XUIs) to gain a deeper understanding of the solutions and design guidelines employed in the academic literature to effectively present explanations to users. To improve the contribution and real-world impact of this survey, we also present a platform to support Human-cEnteRed developMent of Explainable user interfaceS (HERMES) and guide practitioners and scholars in the design and evaluation of XUIs.