Incipit：基于公理支撑的人机文学创作脚手架

中文摘要 AI 辅助

大型语言模型能够根据简短提示生成流畅的散文，但直接的提示到文本交互使作家难以触及塑造长篇叙事的假设。我们提出了Incipit，一个已实现的研究原型，它在作家的意图与生成的散文之间引入了一个显式的规划层。该层以文学公理为基础，这些公理被定义为关于人类经验和叙事技艺的精选且可复用的命题。该原型将一个包含1455条公理和472种类型化关系的知识库与五轮方向对话、一个检索与选择流水线以及一个涵盖创作前提、故事节拍与角色弧线以及章节大纲的三级蓝图相连接。作家可以在将这些结构用作场景生成的上下文之前对其进行查看和编辑。额外的模块支持真实事件抽象和五维诊断反馈。我们描述了系统设计原理、数据流、实现边界以及一个工作设计示例。由于尚未完成受控用户研究或独立评分的输出研究，我们不声称该系统能提高文学质量。相反，我们概述了一项未来的预注册评估，旨在区分公理支撑与层级规划的贡献。本文为在人类与AI协作写作中使用文学知识作为可检查的协调对象提供了一个具体架构。

英文摘要

Large language models can produce fluent prose from short prompts, but direct prompt-to-text interaction gives writers limited access to the assumptions that shape a long narrative. We present Incipit, an implemented research prototype that introduces an explicit planning layer between a writer's intent and generated prose. This layer is grounded in literary axioms, defined as curated and reusable propositions about human experience and narrative craft. The prototype connects a knowledge base of 1455 axioms and 472 typed relationships with a five-round direction dialogue, a retrieval-and-selection pipeline, and a three-level blueprint covering creative premises, story beats and character arcs, and chapter outlines. Writers can inspect and edit these structures before using them as context for scene generation. Additional modules support real-event abstraction and five-dimensional diagnostic feedback. We describe the system design rationale, data flow, implementation boundaries, and a worked design example. As no controlled user study or independently rated output study has yet been completed, we do not claim that the system improves literary quality. Instead, we outline a future preregistered evaluation designed to distinguish the contribution of axiom grounding from that of hierarchical planning. The paper contributes a concrete architecture for using literary knowledge as an inspectable coordination object in human-AI writing.

发表机构

• Noevara Inc.（诺瓦拉公司）
• Centre of Educational Design and Learning, University of Otago（奥塔哥大学教育设计与学习中心）

机构由 AI 辅助整理，请以论文原文为准。