Codified Foreshadowing-Payoff Text Generation

TL;DR

This paper introduces CFPG, a framework that improves story generation by explicitly encoding narrative causal structures, ensuring foreshadowed events are logically fulfilled, thus enhancing long-range narrative coherence in language models.

Contribution

The paper proposes a novel method to encode and utilize causal narrative structures, significantly improving the logical consistency and payoff realization in story generation with LLMs.

Findings

CFPG outperforms standard prompting in payoff accuracy.

Structured supervision improves narrative coherence.

Explicit encoding of narrative mechanics enhances LLM performance.

Abstract

Foreshadowing and payoff are ubiquitous narrative devices through which authors introduce commitments early in a story and resolve them through concrete, observable outcomes. However, despite advances in story generation, large language models (LLMs) frequently fail to bridge these long-range narrative dependencies, often leaving "Chekhov's guns" unfired even when the necessary context is present. Existing evaluations largely overlook this structural failure, focusing on surface-level coherence rather than the logical fulfillment of narrative setups. In this paper, we introduce Codified Foreshadowing-Payoff Generation (CFPG), a novel framework that reframes narrative quality through the lens of payoff realization. Recognizing that LLMs struggle to intuitively grasp the "triggering mechanism" of a foreshadowed event, CFPG transforms narrative continuity into a set of executable causal predicates. By mining and encoding Foreshadow-Trigger-Payoff triples from the BookSum corpus, we provide structured supervision that ensures foreshadowed commitments are not only mentioned but also temporally and logically fulfilled. Experiments demonstrate that CFPG significantly outperforms standard prompting baselines in payoff accuracy and narrative alignment. Our findings suggest that explicitly codifying narrative mechanics is essential for moving LLMs from surface-level fluency to genuine narrative competence.