Search papers, labs, and topics across Lattice.
This paper introduces a multi-stage prompt pipeline for RPG content generation that uses structured JSON to model narrative dependencies between world-building, character creation, and quest design. By enforcing schemas and explicit data flow between stages, the pipeline reduces narrative drift and hallucinations, leading to more coherent and consistent RPG worlds. Human evaluations demonstrate that the pipeline generates logically sound and structurally valid RPG content without quality degradation as complexity increases.
Achieve coherent and scalable RPG world generation by explicitly modeling narrative dependencies between LLM prompts.
Large Language Models (LLMs) have shown strong potential for narrative generation, but their use in complex, multi-layered role-playing game (RPG) worlds is still limited by issues of coherence, controllability, and structural consistency. This paper explores a dependency-aware, multi-stage prompt pipeline for procedural RPG content generation that models narrative dependencies through structured intermediate representations. The approach decomposes generation into sequential stages: world building, non-player character creation, player character creation, campaign-level quest planning, and quest expansion. Each stage conditions on structured JSON outputs from previous stages. By enforcing schemas and explicit data flow, the pipeline reduces narrative drift, limits hallucinations, and supports scalable creation of interconnected narrative elements. The system is evaluated qualitatively through human-centered analysis across multiple independent runs. Outputs are assessed using criteria such as structural completeness, internal consistency, narrative coherence, diversity, and actionability. Results show that the pipeline consistently generates logically sound and structurally valid RPG content, without quality degradation as complexity increases. Separating high-level campaign planning from detailed quest expansion improves both global structure and local storytelling. These findings suggest that dependency-aware prompt pipelines with structured intermediate representations are an effective design pattern for LLM-based procedural content generation. This approach may also generalize to other domains requiring sequential reasoning over evolving contextual states.
