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

2026-04-26

AI Summary

This study investigates narrative agency and role allocation in human–large language model (LLM) collaborative storytelling. By constructing a novel corpus of 87 co-authored stories and applying fine-grained, turn-level quantitative analysis through sentiment analysis, semantic modeling, and directional metrics, the research reveals an asymmetric yet complementary collaboration pattern. Humans predominantly drive semantic novelty and narrative direction, exerting significant influence on subsequent story progression, while the LLM acts as an adaptive amplifier—maintaining coherence and enriching content through emotional alignment and a consistently positive tonal baseline. This work provides an empirical foundation and methodological framework for understanding the mechanisms underlying human–AI co-creation in narrative contexts.

Technology Category

Humans and AI: Human-AI Collaboration / Human-AI TeamingNatural Language Processing: (Large) Language ModelsMachine Learning: Large Multimodal Models (LMMs)

Application Category

Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactionsEconomics, Online Markets and Human Computation: Humans versus LLMs for data annotation and labelingUser Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

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.

Problem

• narrative agency
• human-LLM co-writing
• directional alignment
• semantic novelty
• sentiment alignment

Innovation

• narrative agency
• human-LLM co-writing
• directional alignment
• semantic novelty
• affective alignment