Co-AIdeator: Collaborative Human-AI Ideation through Interactive Visualization of LLM-Generated Design Knowledge


Large Language Models (LLMs) open up a myriad of possibilities for augmenting the idea-generation processes of human designers. However, how human designers can best work with such models is less understood, and the ideas generated by LLM were found to be redundant and fragmented. To address this, we introduce Co-AIdeator, a system that offers structured human-AI collaborative design ideation through organizing LLMs responses into an interactive knowledge graph. The design space for the Co-AIdeator was defined based on insights gleaned from a preliminary study and formative interviews with participants who utilized LLMs for design ideation. Subsequently, we conducted a comprehensive user evaluation study with 24 participants, comparing the Co-AIdeator against a baseline. The results, analyzed quantitatively and qualitatively, unequivocally demonstrated a preference for Co-AIdeator. Moreover, the study affirmed the usability and practicality of the Co-AIdeator. It provides a well-organized framework that empowers users to manage their concepts, especially with the aid of a visual interface. Additionally, it enhances overall efficiency and quality in the ideation process.

In The ACM CHI Conference on Human Factors in Computing Systems 2024
Click the Cite button above to demo the feature to enable visitors to import publication metadata into their reference management software.
Create your slides in Markdown - click the Slides button to check out the example.

Add the publication’s full text or supplementary notes here. You can use rich formatting such as including code, math, and images.