Human planning boosts diversity in AI creative writing teams
What Is the Role for Humans in Creative Writing? Creativity and Diversity in Human-AI Collaboration
Human-Computer Interaction
Summary
When humans and AI work together to write stories, the final stories can be very creative but sometimes too similar. The authors studied how humans and AI can best share tasks in writing by dividing the process into planning, writing, reviewing, and revising steps. They found that having a human do the initial planning helped keep the story diverse and enjoyable, while still benefiting from AI creativity in later stages. This suggests that human roles in creative writing with AI should focus on planning to get the best mix of ideas.
What this means in practice
- •For creative writing teams: Design human-AI workflows where humans plan stories to increase diversity while leveraging AI for later writing stages.
- •For content creation platforms: Integrate human-led planning steps in AI-assisted story generation tools to improve variety and user enjoyment.
Authors
Chenyi Li, Haoyu Hu, Raja Marjieh, Katherine M Collins, Max Kreminski, Ilia Sucholutsky, Dalton Conley, Nori Jacoby
Abstract
As AI agents increasingly participate in creative teamwork, writing emerges from hybrid human-AI teams. Although AI can improve the creativity of individual outputs, these gains may come at the cost of homogenization. What is the best role for human intervention? We introduce a transmission-chain paradigm inspired by cognitive models of writing, with four stages: Plan, Write, Review, and Revise. Each stage receives the previous output and passes its own forward. Using data from 333 participants across 427 stories, we compared creativity, diversity, and enjoyment across human, AI, and hybrid chains. Consistent with prior work, all-AI chains produced more creative but less diverse stories than all-human chains. Introducing a single human into an otherwise all-AI chain increased diversity depending on role. Human planning provided the best balance: it preserved AI-level creativity, increased diversity that persisted through downstream AI stages, and maintained enjoyment. We discuss implications for designing human-in-the-loop creative pipelines.