Existing LLM-based systems for writing long-form stories or story outlines frequently suffer from unnatural pacing, whether glossing over important events or over-elaborating on insignificant details, resulting in a jarring experience for the reader. We propose a CONCrete Outline ConTrol (CONCOCT) system to improve pacing when automatically generating story outlines. We first train a concreteness evaluator to judge which of two events is more concrete (low-level-detailed). This evaluator can then be used to control pacing in hierarchical outline generation; in this work, we explore a vaguest-first expansion procedure that aims for uniform pacing. We further use the evaluator to filter new outline items based on predicted concreteness. Compared to a baseline hierarchical outline generator, humans judge CONCOCT's pacing to be more consistent over 57% of the time across multiple outline lengths; the gains also translate to downstream stories. All code, data, and models are open-sourced.

翻译：现有基于大语言模型的长篇故事或故事大纲写作系统常出现不自然的节奏问题，要么忽略重要事件，要么过度描述无关细节，导致读者体验突兀。我们提出一种"具体提纲控制"（CONCOCT）系统，用于改善自动生成故事大纲时的节奏感。首先训练一个具体性评估器，用于判断两个事件中哪一个更为具体（低层级细节化）。该评估器随后可用于控制分层式大纲生成中的节奏——本研究中探索了一种旨在实现均匀节奏的"最模糊优先"扩展策略。进一步利用该评估器根据预测的具体性过滤新的大纲条目。与基线分层式大纲生成器相比，人类评判者在57%以上的场景中认为CONCOCT在多种大纲长度下的节奏更一致；这些优势也可延续至下游故事生成。所有代码、数据和模型均已开源。