Titlebar

Export bibliographic data
Literature by the same author
plus on the publication server
plus at Google Scholar

 

How to Prompt? Opportunities and Challenges of Zero- and Few-Shot Learning for Human-AI Interaction in Creative Applications of Generative Models

Title data

Dang, Hai ; Mecke, Lukas ; Lehmann, Florian ; Goller, Sven ; Buschek, Daniel:
How to Prompt? Opportunities and Challenges of Zero- and Few-Shot Learning for Human-AI Interaction in Creative Applications of Generative Models.
2022
Event: ACM CHI Conference on Human Factors in Computing Systems - Workshops , 10.05.2022 , Online.
(Conference item: Workshop , Speech with paper )

Official URL: Volltext

Project information

Project title:
Project's official titleProject's id
AI Tools - Continuous Interaction with Computational Intelligence ToolsNo information

Abstract in another language

Deep generative models have the potential to fundamentally change the way we create high-fidelity digital content but are often hard to control. Prompting a generative model is a promising recent development that in principle enables end-users to creatively leverage zero-shot and few-shot learning to assign new tasks to an AI ad-hoc, simply by writing them down. However, for the majority of end-users writing effective prompts is currently largely a trial and error process. To address this, we discuss the key opportunities and challenges for interactive creative applications that use prompting as a new paradigm for Human-AI interaction. Based on our analysis, we propose four design goals for user interfaces that support prompting. We illustrate these with concrete UI design sketches, focusing on the use case of creative writing. The research community in HCI and AI can take these as starting points to develop adequate user interfaces for models capable of zero- and few-shot learning.

Further data

Item Type: Conference item (Speech with paper)
Refereed: Yes
Institutions of the University: Faculties > Faculty of Mathematics, Physics und Computer Science > Department of Computer Science
Faculties
Faculties > Faculty of Mathematics, Physics und Computer Science
Result of work at the UBT: Yes
DDC Subjects: 000 Computer Science, information, general works > 004 Computer science
Date Deposited: 09 Aug 2022 06:53
Last Modified: 09 Aug 2022 06:53
URI: https://eref.uni-bayreuth.de/id/eprint/71428