Papers
arxiv:2210.06774

Re3: Generating Longer Stories With Recursive Reprompting and Revision

Published on Oct 13, 2022
Authors:
,

Abstract

We consider the problem of automatically generating longer stories of over two thousand words. Compared to prior work on shorter stories, long-range plot coherence and relevance are more central challenges here. We propose the Recursive Reprompting and Revision framework (Re3) to address these challenges by (a) prompting a general-purpose language model to construct a structured overarching plan, and (b) generating story passages by repeatedly injecting contextual information from both the plan and current story state into a language model prompt. We then revise by (c) reranking different continuations for plot coherence and premise relevance, and finally (d) editing the best continuation for factual consistency. Compared to similar-length stories generated directly from the same base model, human evaluators judged substantially more of Re3's stories as having a coherent overarching plot (by 14% absolute increase), and relevant to the given initial premise (by 20%).

Community

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2210.06774 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2210.06774 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2210.06774 in a Space README.md to link it from this page.

Collections including this paper 4