<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yang-etal-2022-re3">
    <titleInfo>
        <title>Re3: Generating Longer Stories With Recursive Reprompting and Revision</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Kevin</namePart>
        <namePart type="family">Yang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yuandong</namePart>
        <namePart type="family">Tian</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Nanyun</namePart>
        <namePart type="family">Peng</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Dan</namePart>
        <namePart type="family">Klein</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2022-12</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Abu Dhabi, United Arab Emirates</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <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%).</abstract>
    <identifier type="citekey">yang-etal-2022-re3</identifier>
    <identifier type="doi">10.18653/v1/2022.emnlp-main.296</identifier>
    <location>
        <url>https://aclanthology.org/2022.emnlp-main.296</url>
    </location>
    <part>
        <date>2022-12</date>
        <extent unit="page">
            <start>4393</start>
            <end>4479</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Re3: Generating Longer Stories With Recursive Reprompting and Revision
%A Yang, Kevin
%A Tian, Yuandong
%A Peng, Nanyun
%A Klein, Dan
%S Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F yang-etal-2022-re3
%X 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%).
%R 10.18653/v1/2022.emnlp-main.296
%U https://aclanthology.org/2022.emnlp-main.296
%U https://doi.org/10.18653/v1/2022.emnlp-main.296
%P 4393-4479

Markdown (Informal)

[Re3: Generating Longer Stories With Recursive Reprompting and Revision](https://aclanthology.org/2022.emnlp-main.296) (Yang et al., EMNLP 2022)

• Re3: Generating Longer Stories With Recursive Reprompting and Revision (Yang et al., EMNLP 2022)

ACL

• Kevin Yang, Yuandong Tian, Nanyun Peng, and Dan Klein. 2022. Re3: Generating Longer Stories With Recursive Reprompting and Revision. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 4393–4479, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.