Partnering with Generative AI: Experimental Evaluation of Human-Led and Model-Led Interaction in Human-AI Co-Creation

TL;DR

This study compares human-led and model-led interaction modes in human-AI co-creation, revealing that model-led approaches improve idea quality but may reduce diversity and ownership, emphasizing the importance of reflective AI collaboration.

Contribution

It provides an experimental evaluation of different human-AI interaction modes, highlighting the benefits and trade-offs of model-led versus human-led collaboration in creative tasks.

Findings

Model-led mode improves idea quality

Human-led mode preserves idea diversity and ownership

Reflective AI collaboration enhances creative processes

Abstract

Large language models (LLMs) show strong potential to support creative tasks, but the role of the interface design is poorly understood. In particular, the effect of different modes of collaboration between humans and LLMs on co-creation outcomes is unclear. To test this, we conducted a randomized controlled experiment ($N = 486$) comparing: (a) two variants of reflective, human-led modes in which the LLM elicits elaboration through suggestions or questions, against (b) a proactive, model-led mode in which the LLM independently rewrites ideas. By assessing the effects on idea quality, diversity, and perceived ownership, we found that the model-led mode substantially improved idea quality but reduced idea diversity and users' perceived idea ownership. The reflective, human-led mode also improved idea quality, yet while preserving diversity and ownership. We independently validated the findings in a different context ($N = 640$). Our findings highlight the importance of designing interactions with generative AI systems as reflective thought partners that complement human strengths and augment creative processes.