Survey on User Interface Design and Interactions for Generative AI Applications
By Reuben Luera, University of California, USA, rluera@berkeley.edu | Ryan Rossi, Adobe Research, USA | Alexa Siu, Adobe Research, USA | Franck Dernoncourt, Adobe Research, USA | Tong Yu, Adobe Research, USA | Sungchul Kim, Adobe Research, USA | Ruiyi Zhang, Adobe Research, USA | Xiang Chen, Adobe Research, USA | Hanieh Salehy, Adobe Research, USA | Nedim Lipka, Adobe Research, USA | Samyadeep Basu, University of Maryland, USA | Puneet Mathur, Adobe Research, USA | Jian Zhao, University of Waterloo, Canada
Abstract
The applications of generative AI are diverse and impressive, and the interplay between users and AI in shaping these applications’ impact is crucial. Current human-AI interaction literature has taken a broad look at how humans interact with generative AI, but it merits a deeper look into 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 on explicit, user-initiated interactions and implicit, system-driven engagements, addressing how these approaches tackle critical issues, such as how generative AI applications can best be designed to meet user agency and control needs. 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.
Survey on User Interface Design and Interactions for Generative AI Applications
The applications of generative AI are diverse and impressive, and the interplay between users and AI in shaping these applications’ impact is crucial. Current human-AI interaction literature has taken a broad look at how humans interact with generative AI, but it merits a deeper look into the user interface designs and patterns used to create these applications. This monograph 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. The focus is on explicit, user-initiated interactions and implicit, system-driven engagements, addressing how these approaches tackle critical issues, such as how generative AI applications can best be designed to meet user agency and control needs.
The monograph aims to create a compendium of different user-interaction patterns that can be used as a reference for designers and developers alike. In doing so, it should make the entry barrier easier for those attempting to learn more about the design of generative AI applications.
