Re3: Generating Longer Stories With Recursive Reprompting and Revision

Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 4393 - 4479 December 7-11, 2022 ©2022 Association for Computational Linguistics Re3: Generating Longer Stories With Recursive Reprompting and Revision Kevin Yang1 Yuandong Tian2 Nanyun Peng3 Dan Klein1 1UC Berkeley, 2Meta AI, 3UCLA {yangk,klein}@berkeley.edu,yuandong@meta.com,violetpeng@cs.ucla.edu Abstract We consider the problem of automatically gen- erating longer stories of over two thousand words. Compared to prior work on shorter stories, long-range plot coherence and rele- vance are more central challenges here. We propose the Recursive Reprompting and Re- vision framework (Re3) to address these chal- lenges by (a) prompting a general-purpose lan- guage model to construct a structured overar- ching 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 con- sistency. 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%). 1 Introduction Generating long-term coherent stories is a long- standing challenge for artificial intelligence, requir- ing a comprehensive grasp of linguistic, world, and commonsense knowledge (Charniak, 1972; Turner, 1994). Recently, many works have automatically generated short stories ranging in length from five sentences to one or two paragraphs (Fan et al., 2018; Yao et al., 2019; Goldfarb-Tarrant et al., 2020; Rashkin et al., 2020; Han et al., 2022). While stories of such length serve as a good test bed for text generation, they are much shorter than typical short stories meant for human consumption, which are often several pages in length. In this work, we aim to bridge some of this gap by generating much longer “short” stories: the final generated stories in our experiments are 2000-2500 words. We are the first to automatically generate plot-coherent stories of such length, with further Generate a setting, characters, and outline by prompting a language model. A new law grad returns home to start her career, but struggles with the broken justice system. Liza Turner pulled up in front of the house where she’d grown up. Little had changed since she was a teenager... Write story continuations by prompting based on the plan and previous story. Rerank story continuations for plot coherence and premise relevance. Edit selected continuation to maintain long-range factual consistency. Plan Draft Rewrite Edit Premise Story Figure 1: High-level overview of Re3. length increases limited primarily by evaluation rather than technical issues.1 Generating stories of such length faces qualitatively new challenges compared to prior work on shorter stories. First, the system must maintain a coherent overarching plot over thousands of words. Given an initial premise, it should maintain relevance to this premise over thousands of words as well. Additional challenges include preservation of narration style and avoiding factual contradictions over a very long …

Content truncated to 500 words