paper-with-me

Papers

Re3: Generating Longer Stories With Recursive Reprompting and Revision

2022-10-13 · Kevin Yang, Yuandong Tian, Nanyun Peng, Dan Klein

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%).

📄 PDF Abstract BibTeX arXiv:2210.06774

Code (1)

yangkevin2/emnlp22-re3-story-generation 공식 구현 pytorch

Tasks

Language ModelingLanguage ModellingReranking

Methods 이 논문이 사용한 방법론

BASE 설명 없음

Similar Papers 제목 키워드 기반

ReVisionLLM: Recursive Vision-Language Model for Temporal Grounding in Hour-Long Videos

2024-11-22 · CVPR 2025 1 · Tanveer Hannan, Md Mohaiminul Islam, Jindong Gu, Thomas Seidl 외

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 Retrieval

NewsEdits: A Dataset of Revision Histories for News Articles (Technical Report: Data Processing)

2021-04-19 · Alexander Spangher, Jonathan May

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…

Articles

Endogenous Reprompting: Self-Evolving Cognitive Alignment for Unified Multimodal Models

2026-01-28 · Zhenchen Tang, Songlin Yang, Zichuan Wang, Bo Peng 외 arxiv

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 Learning

One Document, Many Revisions: A Dataset for Classification and Description of Edit Intents

2022-06-01 · LREC 2022 6 · Dheeraj Rajagopal, Xuchao Zhang, Michael Gamon, Sujay Kumar Jauhar 외

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

2023-05-17 · Weijia Xu, Andrzej Banburski-Fahey, Nebojsa Jojic

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…