面向创意故事生成的集体批评者框架
Collective Critics for Creative Story Generation
AI总结：
本文提出CritiCS框架，通过多LLM批评者与领导者协作的多轮修订机制，在保持叙事连贯性的同时提升长篇故事生成的创意性与读者参与度，并支持人机交互式写作。
摘要：
使用大型语言模型（LLMs）生成具有叙事连贯性的数千字长故事一直是一项具有挑战性的任务。以往研究通过提出不同的框架来应对这一挑战，这些框架先创建故事计划，再基于该计划生成长篇故事。然而，这些框架主要侧重于维持故事中的叙事连贯性，往往忽视了故事计划的创意性以及由这些计划生成的故事的表现力，而这两者都是吸引读者兴趣的理想特性。在本文中，我们提出了面向创意故事生成的集体批评者框架（CritiCS），该框架由计划精炼阶段（CrPlan）和故事生成阶段（CrText）组成，旨在将一种促进上述特性的集体修订机制融入长篇故事生成过程。具体而言，在每个阶段中，一组LLM批评者与一位领导者协作，通过多轮迭代逐步精炼计划和故事的草稿。广泛的人类评估表明，CritiCS能够显著提升故事创意性和读者参与度，同时保持叙事连贯性。此外，该框架的设计允许人类作者以批评过程中任意角色积极参与，从而实现故事写作中的人机交互式协作。
英文摘要：
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.
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。
