[CHI26] NarrativeLoom: Enhancing Creative Storytelling through Multi-Persona Collaborative Improvisation
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 (BVSR) theory. NarrativeLoom deploys specialized 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.
Yuxi Ma (Yuki)
Ph.D. '24
My research interests include psychology-inspired AI research to understand and model human behavior and cognition, as well as investigating machine creativity and its applications in art.
Yongqian Peng
Tong Class '21
My research interests include Ai+psychology, human computer interaction and computer vision etc.
Fengyuan Yang
Tong Class '24
Chi Zhang
Research Scientist
Zilong Zheng
Research Scientist
