NarrativeLoom: Enhancing Creative Storytelling through Multi-Persona Collaborative Improvisation
CHI · 2026
Abstract
Large Language Models show promise for AI-assisted storytelling, yet current tools often generate predictable, unoriginal narratives. To address this limitation, we present NarrativeLoom, a multi-persona co-creative system grounded in Campbell’s Blind Variation and Selective Retention theory. NarrativeLoom deploys specialized Artificial Intelligence (AI ) personas to generate diverse narrative options (blind variation), while users act as creative directors to select and refine them (selective retention). We designed a controlled study with 50 participants and found that stories co-authored with NarrativeLoom were not only perceived by users as more novel and diverse but were also objectively rated by experts as significantly better across all Torrance Test creativity dimensions: fluency, flexibility, originality, and elaboration. Stories are significantly longer with richer settings and more dialogue. Writing expertise emerged as a moderator: novices benefited more from structured scaffolding. This demonstrates the value of theory-informed co-creative systems and the importance of adapting them to varying user expertise.
Citation
@misc{chen2025imtalkerefficientaudiodriventalking,
title={IMTalker: Efficient Audio-driven Talking Face Generation with Implicit Motion Transfer},
author={Bo Chen and Tao Liu and Qi Chen and Xie Chen and Zilong Zheng},
year={2025},
eprint={2511.22167},
archivePrefix={arXiv},
primaryClass={cs.CV},
url={https://arxiv.org/abs/2511.22167},
}