Explainability to enhance creativity : A human-centered approach to prompt engineering and task allocation in text-to-image models for design purposes
Year: 2023
Type: dissertation
Abstract: As the power, utility, and prevalence of generative AI technologies continue to grow, the debate on whether and how designers should incorporate text-image models into the design process is gaining momentum. To ensure productivity, creativity, and human values, this project seeks to address design interaction and task allocation between designers, and generative AI models become essential. Explainability is a growing area of research, although many of the explanations to enhance interpretability and transparency in ML models target ML engineers rather than end users. This project investigates what kind of explanations the designers would need to communicate with the models successfully. Through a participatory design approach, this project resulted in some key findings regarding the creative nature of using natural language to express design, how experience using generative AI models affects how you use them, and how designers can benefit from recognizing the model as creative. The project resulted in two concepts for enhancing the user experience of prompt engineering, one targeting user behavior and the other improving explainability and transparency in image-generative AI models.
Author: Burlin, Celina
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7047169379