Pith. sign in

REVIEW 5 cited by

Re3: Generating Longer Stories With Recursive Reprompting and Revision

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2210.06774 v3 pith:2ENUI3RB submitted 2022-10-13 cs.CL cs.AI

Kevin Yang , Yuandong Tian , Nanyun Peng , Dan Klein This is my paper
classification cs.CLcs.AI
keywords storiesgeneratingmodelplotchallengescoherencecomparedlanguage
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original 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%).

Discussion (0). Sign in to comment.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. NarrativeWorldBench: A Frontier-Saturated Benchmark and a Latent World Model for Long-Horizon Co-Creative Audio Drama

    cs.CL 2026-06 unverdicted novelty 6.0 of 10

    NarrativeWorldBench evaluates 21 LLMs on nine narrative metrics across horizons to 200 episodes and introduces N-VSSM, a 256-dimensional variational state-space model that achieves plot-beat F1 >=0.84 with 4x lower co...

  2. Unveiling Privacy Risks in Multi-modal Large Language Models: Task-specific Vulnerabilities and Mitigation Challenges

    cs.CR 2026-06 unverdicted novelty 6.0 of 10

    Introduces MM-Privacy dataset and evaluations showing MLLMs leak sensitive data from images in various tasks, highlighting task inconsistency effects.

  3. LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code

    cs.SE 2024-03 unverdicted novelty 6.0 of 10

    LiveCodeBench collects 400 recent contest problems to create a contamination-free benchmark evaluating LLMs on code generation and related capabilities like self-repair and execution.

  4. From Personas to Plot: Character-Grounded Multi-Agent Story Generation for Long-Form Narratives

    cs.CL 2026-07 unverdicted novelty 5.0 of 10

    MAGNET multi-agent generation with persona grounding and ATLAS graph verification yields 34-50% fewer hallucinations and annotations than single-model or IBSEN baselines at 100-page scale.

  5. Mind DeepResearch Technical Report

    cs.AI 2026-04 unverdicted novelty 5.0 of 10

    MindDR combines a Planning Agent, DeepSearch Agent, and Report Agent with SFT cold-start, Search-RL, Report-RL, and preference alignment to reach competitive scores on research benchmarks using 30B-scale models.

Pith tools