Creative Momentum Transfer: How Timing and Labeling of AI Suggestions Shape Iterative Human Ideation

Abstract

Human–AI collaboration is increasingly integral to a variety of domains where creative ideation unfolds in iterative cycles, yet most existing studies evaluate AI-generated concepts in a single step. This paper addresses the gap by investigating “Creative Momentum Transfer”—how the timing (early vs. late) and labeling (AI-labeled vs. unlabeled) of AI prompts shape multi-round human ideation. In a between-subjects experiment (N = 247), participants proposed solutions for plastic pollution over two rounds, with AI suggestions introduced either at the outset or mid-process and labeled explicitly or not. Results reveal that early AI prompts increase overall creativity but induce stronger anchoring, whereas late AI prompts trigger a mid-round pivot that fosters more divergent thinking yet still boosts final outcomes compared to a no-AI control. Labeling amplifies both subjective and objective adoption of AI ideas, although most participants could detect AI sources even when unlabeled. Furthermore, qualitative interviews highlight nuanced perspectives on perceived ownership, authenticity, and the ways in which labeling triggers deeper scrutiny of the AI’s style. By demonstrating that baseline creativity moderates these effects more robustly than trust in AI, this study advances our theoretical understanding of multi-round human–AI synergy while offering design guidelines for next-generation creativity support systems. We discuss how user-centered design can balance rapid convergence (via early AI) with strategic pivot opportunities (via late AI) and weigh transparent labeling against ethical considerations of authorship and user autonomy.