SWAG: Storytelling With Action Guidance

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Patel, Zeeshan, El-Refai, Karim, Pei, Jonathan, Li, Tianle
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866916425597190144
author Patel, Zeeshan
El-Refai, Karim
Pei, Jonathan
Li, Tianle
author_facet Patel, Zeeshan
El-Refai, Karim
Pei, Jonathan
Li, Tianle
contents Automated long-form story generation typically employs long-context large language models (LLMs) for one-shot creation, which can produce cohesive but not necessarily engaging content. We introduce Storytelling With Action Guidance (SWAG), a novel approach to storytelling with LLMs. Our approach frames story writing as a search problem through a two-model feedback loop: one LLM generates story content, and another auxiliary LLM is used to choose the next best "action" to steer the story's future direction. Our results show that SWAG can substantially outperform previous end-to-end story generation techniques when evaluated by GPT-4 and through human evaluation. Our SWAG pipeline using only small open-source models surpasses GPT-3.5-Turbo.
format Preprint
id arxiv_https___arxiv_org_abs_2402_03483
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle SWAG: Storytelling With Action Guidance
Patel, Zeeshan
El-Refai, Karim
Pei, Jonathan
Li, Tianle
Computation and Language
Artificial Intelligence
Automated long-form story generation typically employs long-context large language models (LLMs) for one-shot creation, which can produce cohesive but not necessarily engaging content. We introduce Storytelling With Action Guidance (SWAG), a novel approach to storytelling with LLMs. Our approach frames story writing as a search problem through a two-model feedback loop: one LLM generates story content, and another auxiliary LLM is used to choose the next best "action" to steer the story's future direction. Our results show that SWAG can substantially outperform previous end-to-end story generation techniques when evaluated by GPT-4 and through human evaluation. Our SWAG pipeline using only small open-source models surpasses GPT-3.5-Turbo.
title SWAG: Storytelling With Action Guidance
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2402.03483