NarrativeLoom: Enhancing Creative Storytelling through Multi-Persona Collaborative Improvisation
This work provides a theory-informed co-creative system that enhances the novelty and diversity of AI-assisted storytelling, benefiting both novice and expert writers.
This paper tackles the problem of predictable narratives generated by current AI storytelling tools by introducing NarrativeLoom, a multi-persona co-creative system. A study with 50 participants found that stories co-authored with NarrativeLoom were perceived as more novel and diverse by users and objectively rated by experts as significantly better across all Torrance Test creativity dimensions.
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 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.