Survey of User Interface Design and Interaction Techniques in Generative AI Applications
Reuben Luera, Ryan A. Rossi, Alexa Siu, Franck Dernoncourt, Tong Yu, Sungchul Kim, Ruiyi Zhang, Xiang Chen, Hanieh Salehy, Jian Zhao, Samyadeep Basu, Puneet Mathur, Nedim Lipka
2024-11-04
Summary
This paper surveys how users interact with generative AI applications, focusing on the design of user interfaces (UI) and the techniques used to enhance user experience. It aims to provide a comprehensive overview of user interaction patterns and guide designers in creating better generative AI tools.
What's the problem?
While generative AI applications have become impressive, there is a lack of detailed information about the specific user interface designs and interaction techniques that make these applications effective. Most existing literature does not clearly outline how users interact with these systems, which can lead to less effective designs.
What's the solution?
The authors conducted a survey that categorizes different ways users interact with generative AI, particularly focusing on user-guided interactions. They created a reference guide for designers and developers, highlighting various interaction patterns that can be applied to meet the needs of different use cases. This resource aims to lower the barriers for those looking to learn about designing generative AI applications.
Why it matters?
This research is important because it helps improve how we design and interact with generative AI tools. By understanding user interaction patterns better, designers can create more intuitive and effective applications, making it easier for users to leverage the power of generative AI in their tasks. This can lead to better user experiences and wider adoption of AI technologies.
Abstract
The applications of generative AI have become extremely impressive, and the interplay between users and AI is even more so. Current human-AI interaction literature has taken a broad look at how humans interact with generative AI, but it lacks specificity regarding the user interface designs and patterns used to create these applications. Therefore, we present a survey that comprehensively presents taxonomies of how a human interacts with AI and the user interaction patterns designed to meet the needs of a variety of relevant use cases. We focus primarily on user-guided interactions, surveying interactions that are initiated by the user and do not include any implicit signals given by the user. With this survey, we aim to create a compendium of different user-interaction patterns that can be used as a reference for designers and developers alike. In doing so, we also strive to lower the entry barrier for those attempting to learn more about the design of generative AI applications.