Humans create stories while AI models expand and refine them
Humans Introduce, Models Elaborate: Asymmetric Narrative Agency in Human-LLM Co-Writing
Human-Computer Interaction
Summary
This paper looks at how humans and AI language models work together to tell stories, comparing team-ups of two humans, a human with an AI, and two AIs. The authors found that when humans and AI collaborate, humans usually come up with new story ideas, while the AI focuses on improving and keeping the story consistent. This means AI models act more like helpers who build on human ideas rather than equal partners creating stories from scratch. The study helps us understand the unique roles humans and AI play in creative writing.
Human-LLM co-writingCollaborative storytellingNarrative agencySemantic noveltyValence adaptationTurn-based interactionLanguage modelsStory elaborationNarrative alignmentCreative writing AI
Authors
Halfdan Nordahl Fundal, Yuri Bizzoni, Charlotte Gjørup Bilde, Ida Bække Johannesen, Rebekah Baglini
Abstract
Human-LLM co-writing is increasingly used for open-ended text generation, but much prior work focuses on final outputs rather than the interactional dynamics through which stories are produced. We study turn-based collaborative storytelling across three matched conditions: Human-Human (HH), Human-LLM (HA), and LLM-LLM (AA). Using a shared storytelling paradigm, we measure how agents align, introduce novel material, and influence narrative development through turn-level measures of valence adaptation, semantic novelty, transience, and resonance. Our results show that HA co-writing is not intermediate between HH and AA collaboration. Instead, it displays a distinctive asymmetry where humans tend to introduce more novel and persistent narrative material, while LLMs tend to elaborate and stabilize the existing context. These findings suggest that, in this setting, LLMs function less as human co-authors and more as adaptive narrative amplifiers that reshape how agency is distributed in collaborative writing.