Human-AI Schema Discovery and Application for Creative Problem Solving

TL;DR

This paper presents a framework for human-AI collaboration in discovering and applying structural schemas to enhance creative problem solving across various domains.

Contribution

It introduces systems that assist users in sensemaking and operationalizing schemas, improving transparency and collaboration in human-AI interactions.

Findings

Supports sensemaking over examples to abstract schemas

Facilitates operationalizing schemas into co-creative workflows

Enhances accessibility and actionability of implicit knowledge

Abstract

Humans often rely on underlying structural patterns-schemas-to create, whether by writing stories, designing software, or composing music. Schemas help organize ideas and guide exploration, but they are often difficult to discover and apply, especially in complex or unfamiliar domains. My Ph.D. research develops a framework for human-AI schema discovery and application to support creative problem solving. I design systems that support users in sensemaking over examples to abstract schemas, and in operationalizing schemas into human-AI co-creative workflows for application. This research offers insights into how schema-guided interaction can make implicit knowledge more accessible and actionable, advancing more transparent and collaborative human-AI systems.