CLFeb 27, 2024

Creating Suspenseful Stories: Iterative Planning with Large Language Models

arXiv:2402.17119v1116 citationsh-index: 7EACL
Originality Highly original
AI Analysis

This addresses the under-explored challenge of suspense in AI-generated stories for NLP and storytelling applications, representing a first attempt in this area.

The paper tackles the problem of generating suspenseful stories using large language models, which are unreliable for this task, by proposing a novel iterative-prompting-based planning method grounded in cognitive psychology and narratology, resulting in effective suspenseful stories as demonstrated through extensive human evaluations.

Automated story generation has been one of the long-standing challenges in NLP. Among all dimensions of stories, suspense is very common in human-written stories but relatively under-explored in AI-generated stories. While recent advances in large language models (LLMs) have greatly promoted language generation in general, state-of-the-art LLMs are still unreliable when it comes to suspenseful story generation. We propose a novel iterative-prompting-based planning method that is grounded in two theoretical foundations of story suspense from cognitive psychology and narratology. This theory-grounded method works in a fully zero-shot manner and does not rely on any supervised story corpora. To the best of our knowledge, this paper is the first attempt at suspenseful story generation with LLMs. Extensive human evaluations of the generated suspenseful stories demonstrate the effectiveness of our method.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes