As large-scale language models become the standard for text generation, there
is a greater need to tailor the generations to be more or less concise,
targeted, and informative, depending on the audience/application. Existing
control approaches primarily adjust the semantic (e.g., emotion, topics),
structural (e.g., syntax tree, parts-of-speech), and lexical (e.g.,
keyword/phrase inclusion) properties of text, but are insufficient to
accomplish complex objectives such as pacing which control the complexity and
readability of the text. In this paper, we introduce CEV-LM - a lightweight,
semi-autoregressive language model that utilizes constrained edit vectors to
control three complementary metrics (speed, volume, and circuitousness) that
quantify the shape of text (e.g., pacing of content). We study an extensive set
of state-of-the-art CTG models and find that CEV-LM provides significantly more
targeted and precise control of these three metrics while preserving semantic
content, using less training data, and containing fewer parameters.

本文介绍了 CEV-LM，一种轻量级半自回归语言模型，利用约束编辑向量来控制文本的速度、音量和曲折度这三个衡量文本形状的指标，研究表明 CEV-LM 能够更精确地控制这三个指标，同时保持语义内容、使用更少的训练数据和参数。

CEV-LM：控制编辑向量语言模型用于塑造自然语言生成

CEV-LM: Controlled Edit Vector Language Model for Shaping Natural  Language Generations

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.

通过训练一个具有判定具体（低层次详细）程度的评估器，我们提出了一个名为 CONCrete Outline ConTrol（CONCOCT）的系统，该系统在自动生成故事大纲时改善了情节掌控，通过模糊化的首次扩展过程来实现统一的情节掌控；评估器还可用于基于预测的具体程度对新的大纲项目进行过滤，相比基线分层大纲生成器，人们在多个大纲长度上 57% 的时间内判断 CONCOCT 的情节掌控更为一致，并且这种优势也体现在后续的故事中。