Directional Alignment and Narrative Agency in Human-LLM Co-Writing

TL;DR

This study analyzes how humans and language models collaborate in storytelling, revealing humans mainly drive narrative innovation while LLMs adaptively elaborate and maintain coherence.

Contribution

It introduces a new corpus and quantitative methods to assess influence, sentiment, and semantic novelty in human-LLM co-writing, highlighting asymmetric roles.

Findings

Humans introduce more semantic novelty and influence story direction.

LLMs adapt emotionally and elaborate on human contributions.

Both agents track each other's emotional valence, with LLMs tending to more positive baselines.

Abstract

We investigate narrative agency in human-LLM creative co-writing, asking who drives story development in turn-based collaboration. Using a new corpus of 87 human-LLM co-written stories, we apply sentiment and semantic modeling to quantify affective alignment and semantic novelty in turn-taking, and directional measures to assess which agent shapes narrative progression. Our results show asymmetric influence: human turns introduce greater semantic novelty and are more likely to shape subsequent developments, whereas LLM contributions predominantly elaborate on human-introduced elements. At the sentiment level, alignment is also asymmetric, but more bidirectional: LLMs exhibit stronger turn-level emotional adaptation than humans, but both agents track each other's emotional valence and LLMs show an independent tendency to more positive emotional baselines. These findings indicate a complementary division of labor in human-LLM co-writing, where humans drive narrative innovation and direction, while LLMs act as adaptive amplifiers that sustain coherence and elaborate emerging narratives.