Improving Pacing in Long-Form Story Planning

Yichen Wang, Kevin Yang, Xiaoming Liu, Dan Klein


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.
Anthology ID:
2023.findings-emnlp.723
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2023
Month:
December
Year:
2023
Address:
Singapore
Editors:
Houda Bouamor, Juan Pino, Kalika Bali
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
10788–10845
Language:
URL:
https://aclanthology.org/2023.findings-emnlp.723
DOI:
10.18653/v1/2023.findings-emnlp.723
Bibkey:
Cite (ACL):
Yichen Wang, Kevin Yang, Xiaoming Liu, and Dan Klein. 2023. Improving Pacing in Long-Form Story Planning. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 10788–10845, Singapore. Association for Computational Linguistics.
Cite (Informal):
Improving Pacing in Long-Form Story Planning (Wang et al., Findings 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.findings-emnlp.723.pdf