NarrativeLoom：通过多角色协作即兴创作增强创造性叙事
NarrativeLoom: Enhancing Creative Storytelling through Multi-Persona Collaborative Improvisation
AI总结：
NarrativeLoom通过多角色协作即兴创作提升叙事原创性，通过理论指导的协作系统增强创造性输出。
摘要：
大型语言模型在AI辅助叙事中展现出潜力，但当前工具往往生成可预测、不原创的叙事。为解决这一限制，我们提出了NarrativeLoom，一种基于Campbell的盲变与选择保留理论的多角色协作创作系统。NarrativeLoom部署了专门的AI角色生成多样化的叙事选项（盲变），而用户则作为创意导演选择和精炼它们（选择保留）。我们设计了一项包含50名参与者的受控研究，发现与NarrativeLoom共同创作的故事不仅被用户认为更加新颖和多样，而且由专家客观评价在所有Torrance测试创造力维度上（流畅性、灵活性、原创性和扩展性）都显著更好。故事更长，设定更丰富，对话更多。写作能力 emerged as 一个调节变量：初学者从结构化的支架中受益更多。这展示了理论指导的协作创作系统的价值，并强调了根据不同用户能力调整它们的重要性。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
