Re3: Generating Longer Stories With Recursive Reprompting and Revision
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%).
Code (1)
Tasks
Language ModelingLanguage ModellingRerankingMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
ReVisionLLM: Recursive Vision-Language Model for Temporal Grounding in Hour-Long Videos
Large language models (LLMs) excel at retrieving information from lengthy text, but their vision-language counterparts (VLMs) face difficulties with hour-long videos, especially for temporal grounding. Specifically, thes…
Language-Based Temporal LocalizationLanguage ModelingLanguage ModellingNatural Language Moment RetrievalNewsEdits: A Dataset of Revision Histories for News Articles (Technical Report: Data Processing)
News article revision histories have the potential to give us novel insights across varied fields of linguistics and social sciences. In this work, we present, to our knowledge, the first publicly available dataset of ne…
ArticlesEndogenous Reprompting: Self-Evolving Cognitive Alignment for Unified Multimodal Models
Unified Multimodal Models (UMMs) exhibit strong understanding, yet this capability often fails to effectively guide generation. We identify this as a Cognitive Gap: the model lacks the understanding of how to enhance its…
Reinforcement LearningOne Document, Many Revisions: A Dataset for Classification and Description of Edit Intents
Document authoring involves a lengthy revision process, marked by individual edits that are frequently linked to comments. Modeling the relationship between edits and comments leads to a better understanding of document …
Reprompting: Automated Chain-of-Thought Prompt Inference Through Gibbs Sampling
We introduce Reprompting, an iterative sampling algorithm that automatically learns the Chain-of-Thought (CoT) recipes for a given task without human intervention. Through Gibbs sampling, Reprompting infers the CoT recip…