創意故事生成的集體評論者

Collective Critics for Creative Story Generation

October 3, 2024

作者: Minwook Bae, Hyounghun Kim

cs.AI

摘要

利用大型語言模型（LLMs）生成幾千字長的故事並保持敘事連貫一直是一項具有挑戰性的任務。先前的研究通過提出不同的框架來應對這一挑戰，這些框架會創建故事計劃並基於該計劃生成一個長篇故事。然而，這些框架主要著眼於在故事中保持敘事連貫，往往忽略了故事計劃中的創意以及從這些計劃生成的故事的表現力，這些是吸引讀者興趣的理想特性。在本文中，我們提出了用於創意故事生成的集體評論框架（CritiCS），由計劃細化階段（CrPlan）和故事生成階段（CrText）組成，以整合一個促進這些特性的集體修訂機制進入長篇故事生成過程。具體來說，在每個階段，一組LLM評論家和一名領導者合作，通過多輪逐步完善計劃和故事草稿。廣泛的人類評估顯示，CritiCS能夠顯著增強故事的創造力和讀者參與度，同時保持敘事連貫。此外，該框架的設計允許人類作家在評論過程中的任何角色中積極參與，實現了故事創作中人機互動合作。

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.