Exploration vs. Fixation: Scaffolding Divergent and Convergent Thinking for Human-AI Co-Creation with Generative Models

TL;DR

This paper introduces HAICo, a human-AI co-creation system that uses divergent and convergent modes to enhance creativity and exploration in image generation, addressing limitations of traditional chatbots.

Contribution

The paper presents a novel co-creation system grounded in the Geneplore model, enabling switchable modes for exploration and refinement to improve creative outcomes.

Findings

HAICo outperforms ChatGPT in creativity and usability.

Switchable modes facilitate broader exploration and targeted refinement.

Scaffolded co-creation enhances creative image generation.

Abstract

Generative AI has democratized content creation, but popular chatbot-based interfaces often prioritize execution, generating fully rendered artifacts right away. This issue can lead to premature convergence and design fixation, where users are being anchored to initial outputs. Recent works have proposed new interfaces to address this issue by supporting exploration, though typically constrained to be semantically close to a user's initial task framing, potentially limiting the creativity of the outcomes. We examine an approach grounded in the Geneplore model of creative cognition and instantiate it in a human-AI co-creation system, HAICo, for creative image generation. HAICo explicitly structures the creative process into two switchable modes: DIVERGENT mode scaffolds the broad exploration of remote conceptual ideas; CONVERGENT mode supports a targeted refinement of selected ideas. Through a within-subjects study (N=24) on a poster image creation task, we demonstrate that HAICo outperforms ChatGPT across multiple dimensions of creativity and usability. Our results highlight the critical need to shift from pure execution-focused chatbots to scaffolded co-creation systems that actively guide exploration and foster the creative process.