BioSpark: Beyond Analogical Inspiration to LLM-augmented Transfer

We present BioSpark a system for analogical innovation designed to act as a creativity partner in reducing the cognitive effort in finding, mapping, and creatively adapting diverse inspirations. While prior approaches have focused on initial stages of identifying inspirations, typically limited to a narrow set of hand coded data, BioSpark uses LLMs embedded in a familiar, visual, Pinterest-like interface to support users in deeply engaging with inspirations across multiple stages of analogical innovation while avoiding fixation and over-reliance. We introduce several novel features, including a tree-of-life enabled approach for generating relevant and diverse inspirations; `Sparks' for analogical transfer; `Trade-offs' for elaboration; and `Q&A' for deeper engagement. We evaluated BioSpark through a workshop with professional designers, a pilot study, and a controlled user study, and found BioSpark's potential to embed AI into interfaces seamlessly, promote deeper engagement, and augment human creativity, while mitigating risks of loss of ownership and fixation.

Publication

Hyeonsu Kang, David Chuan-En Lin, Yan-Ying Chen, Matthew Hong, Nikolas Martelaro, Aniket Kittur. . BioSpark: Beyond Analogical Inspiration to LLM-augmented Transfer. CHI 2025.. DOI:

 paper

Video