Improving Pacing in Long-Form Story Planning
Lists
Only you see this
Abstract
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 **CONC**rete **O**utline **C**on**T**rol (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.
BibTeX
@inproceedings{wang2023improving,
author = {Yichen Wang and Kevin Yang and Xiaoming Liu and Dan Klein},
title = {{Improving Pacing in Long-Form Story Planning}},
booktitle = {Conference on Empirical Methods in Natural Language Processing},
year = {2023},
doi = {10.18653/v1/2023.findings-emnlp.723},
}