"It Felt Like Having a Second Mind": Investigating Human-AI Co-creativity in Prewriting with Large Language Models

TL;DR

This work investigates how humans collaborate with large language models during prewriting tasks such as story and slogan creation. Using a three-session qualitative study with 15 participants, the authors identify a three-stage Human-AI Co-creativity process—Ideation, Illumination, and Implementation—where humans predominantly lead but LLMs contribute by generating novel concepts and enriching detail, with initiative shifting across stages. The study documents collaboration breakdowns, strategies, and user perceptions, and offers design implications for prompt strategies, co-creative writing tools, and explainability to support prewriting. By framing uncertainty as a creative asset rather than a flaw, the work highlights opportunities to harness LLM randomness to stimulate divergent thinking and proposes concrete guidelines for building LLM-augmented writing support systems. The findings advance understanding of human–AI creativity, inform CSCW perspectives, and guide the development of next-generation co-creative writing tools.

Abstract

Prewriting is the process of discovering and developing ideas before a first draft, which requires divergent thinking and often implies unstructured strategies such as diagramming, outlining, free-writing, etc. Although large language models (LLMs) have been demonstrated to be useful for a variety of tasks including creative writing, little is known about how users would collaborate with LLMs to support prewriting. The preferred collaborative role and initiative of LLMs during such a creativity process is also unclear. To investigate human-LLM collaboration patterns and dynamics during prewriting, we conducted a three-session qualitative study with 15 participants in two creative tasks: story writing and slogan writing. The findings indicated that during collaborative prewriting, there appears to be a three-stage iterative Human-AI Co-creativity process that includes Ideation, Illumination, and Implementation stages. This collaborative process champions the human in a dominant role, in addition to mixed and shifting levels of initiative that exist between humans and LLMs. This research also reports on collaboration breakdowns that occur during this process, user perceptions of using existing LLMs during Human-AI Co-creativity, and discusses design implications to support this co-creativity process.

Figures (2)

• Figure 1: The Human-AI co-creativity process that exists during prewriting when collaborating with LLMs.
• Figure :