GROVE: A Retrieval-augmented Complex Story Generation Framework with A Forest of Evidence

TL;DR

GROVE is a novel story generation framework that uses retrieval of human-written examples and an evidence forest to produce more complex, credible, and creative stories with intricate plots.

Contribution

It introduces a retrieval-augmented approach with an evidence forest and an 'asking-why' prompting scheme to improve story complexity and credibility beyond existing methods.

Findings

Enhanced story complexity and credibility demonstrated.

Effective retrieval of relevant examples improves plot diversity.

Iterative evidence extraction refines narrative quality.

Abstract

Conditional story generation is significant in human-machine interaction, particularly in producing stories with complex plots. While Large language models (LLMs) perform well on multiple NLP tasks, including story generation, it is challenging to generate stories with both complex and creative plots. Existing methods often rely on detailed prompts to guide LLMs to meet target conditions, which inadvertently restrict the creative potential of the generated stories. We argue that leveraging information from exemplary human-written stories facilitates generating more diverse plotlines. Delving deeper into story details helps build complex and credible plots. In this paper, we propose a retrieval-au\textbf{G}mented sto\textbf{R}y generation framework with a f\textbf{O}rest of e\textbf{V}id\textbf{E}nce (GROVE) to enhance stories' complexity. We build a retrieval repository for target conditions to produce few-shot examples to prompt LLMs. Additionally, we design an ``asking-why'' prompting scheme that extracts a forest of evidence, providing compensation for the ambiguities that may occur in the generated story. This iterative process uncovers underlying story backgrounds. Finally, we select the most fitting chains of evidence from the evidence forest and integrate them into the generated story, thereby enhancing the narrative's complexity and credibility. Experimental results and numerous examples verify the effectiveness of our method.