用群体批评机制提升长篇故事的创意与吸引力。
Collective Critics for Creative Story Generation
- 多轮协作式批评：每阶段由一群LLM与领袖共同迭代优化故事大纲和文本。
- 人类可参与任意角色，实现人机协同创作，提升互动性。
- 实测显著增强故事创意与读者吸引力，同时保持叙事连贯性。
使用大语言模型生成数千字具有叙事连贯性的长篇故事仍具挑战。以往方法多聚焦于保持叙事连贯性，常忽视故事规划中的创意与生成文本的表现力，而这两者对吸引读者至关重要。本文提出集体批评创意故事生成框架（CritiCS），包含计划优化阶段（CrPlan）与文本生成阶段（CrText），通过群体修订机制融入创意与表现力。每个阶段中，一组LLM批评者与一个领导者协作，经多轮迭代逐步优化故事大纲与文本。大规模人工评估显示，CritiCS能显著提升故事创意与读者参与度，同时维持叙事连贯性。此外，该框架支持人类写作者在任何环节主动参与批评过程，实现交互式人机协作创作。
原文摘要 · Abstract (English)
Generating a long story of several thousand words with narrative coherence using Large Language Models (LLMs) has been a challenging task. Previous research has addressed this challenge by proposing different frameworks that create a story plan and generate a long story based on that plan. However, these frameworks have been mainly focusing on maintaining narrative coherence in stories, often overlooking creativity in story planning and the expressiveness of the stories generated from those plans, which are desirable properties to captivate readers' interest. In this paper, we propose Collective Critics for Creative Story Generation framework (CritiCS), which is composed of plan refining stage (CrPlan) and story generation stage (CrText), to integrate a collective revision mechanism that promotes those properties into long-form story generation process. Specifically, in each stage, a group of LLM critics and one leader collaborate to incrementally refine drafts of plan and story throughout multiple rounds. Extensive human evaluation shows that the CritiCS can significantly enhance story creativity and reader engagement, while also maintaining narrative coherence. Furthermore, the design of the framework allows active participation from human writers in any role within the critique process, enabling interactive human-machine collaboration in story writing.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。