Pith. sign in

REVIEW 2 cited by

End-to-end Story Plot Generator

Not yet reviewed by Pith; the record is open.

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 2310.08796 v1 pith:MHLVY3MX submitted 2023-10-13 cs.CL

classification cs.CL
keywords storytextttplotplotse2eplotopenplotcallsgenerator
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
abstract

Story plots, while short, carry most of the essential information of a full story that may contain tens of thousands of words. We study the problem of automatic generation of story plots, which includes story premise, character descriptions, plot outlines, etc. To generate a single engaging plot, existing plot generators (e.g., DOC (Yang et al., 2022a)) require hundreds to thousands of calls to LLMs (e.g., OpenAI API) in the planning stage of the story plot, which is costly and takes at least several minutes. Moreover, the hard-wired nature of the method makes the pipeline non-differentiable, blocking fast specialization and personalization of the plot generator. In this paper, we propose three models, $\texttt{OpenPlot}$, $\texttt{E2EPlot}$ and $\texttt{RLPlot}$, to address these challenges. $\texttt{OpenPlot}$ replaces expensive OpenAI API calls with LLaMA2 (Touvron et al., 2023) calls via careful prompt designs, which leads to inexpensive generation of high-quality training datasets of story plots. We then train an end-to-end story plot generator, $\texttt{E2EPlot}$, by supervised fine-tuning (SFT) using approximately 13000 story plots generated by $\texttt{OpenPlot}$. $\texttt{E2EPlot}$ generates story plots of comparable quality to $\texttt{OpenPlot}$, and is > 10$\times$ faster (1k tokens in only 30 seconds on average). Finally, we obtain $\texttt{RLPlot}$ that is further fine-tuned with RLHF on several different reward models for different aspects of story quality, which yields 60.0$\%$ winning rate against $\texttt{E2EPlot}$ along the aspect of suspense and surprise.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 2 Pith papers

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

  1. LCFO: Long Context and Long Form Output Dataset and Benchmarking

    cs.CL 2024-12 conditional novelty 6.0 of 10

    New benchmark with gradual human summaries and aligned QA pairs shows GPT-4o-mini leads on long-context summarization and expansion, and automatic metrics correlate weakly with human judgment.

  2. Multi-Facet Blending for Faceted Query-by-Example Retrieval

    cs.IR 2024-12 conditional novelty 6.0 of 10

    A synthetic-data augmentation method that decomposes documents into facets and recombines LLM-written similar and dissimilar fragments improves faceted query-by-example retrieval without citation labels.

Pith tools