UI/UX for Generative AI: Taxonomy, Trend, and Challenge

Current technological advancements in Information Technology are closely linked to Generative Artificial Intelligence, enabling the automation of complex tasks such as generating documents, images, videos, audio, and actions. As such tasks can save much human labor and resources, diverse industries are trying to adopt this technology. However, developing a product utilizing Generative AI is a challenging task, partly because it is a new technology and many users are not familiar with it yet. This paper's primary goal is to find a better way to design Generative AI systems, especially from the Human-Computer Interaction perspective. To begin, we propose a taxonomy for Generative AI systems based on their modality, such as text-based, image-based, audio-based, and multi-modal-based systems, and then evaluate them in terms of their usability, because their functionalities should be aligned with the User Interface (UI), leading to a better User Experience (UX). We survey important trends in this area and introduce future applications by touching upon the issue of explainable AI. Although Generative AI has a bright future, it faces formidable challenges in our industries and society. It is hoped that the taxonomy and research findings presented here will be a useful framework for future research in Generative AI systems and their UI/UX.