Schemex: Discovering Structural Abstractions from Examples
This addresses the difficulty in schema induction for creative and communicative domains like storytelling, software, and music, offering an incremental improvement over existing methods.
The paper tackles the problem of discovering implicit structural patterns (schemas) from examples, which is challenging due to surface-level variation and balancing generality. It presents Schemex, an interactive AI workflow that produces more actionable schemas than a baseline without sacrificing generalizability, as shown in studies.
Creative and communicative work is often underpinned by implicit structures, such as the Hero's Journey in storytelling, design patterns in software, or chord progressions in music. People often learn these structures from examples - a process known as schema induction. However, because schemas are abstract and implicit, they are difficult to discover: shared structural patterns are obscured by surface-level variation, and balancing generality with specificity is challenging. We present Schemex, an interactive AI workflow that systematically supports schema induction by decomposing it into three tractable stages: clustering examples, abstracting candidate schemas, and contrastively refining them by generating new instances and comparing against originals. Studies show that Schemex produces more actionable schemas than a frontier baseline without sacrificing generalizability, with participants uncovering deep and nuanced structural patterns. We also discuss design implications for the cognitive role of interactive process in structure discovery.