Symbolically Scaffolded Play: Designing Role-Sensitive Prompts for Generative NPC Dialogue
This addresses the problem of designing effective prompts for generative NPC dialogue in games, showing that constraints are not inherently beneficial and offering a framework for balancing coherence and improvisation, though it is incremental as it builds on existing fuzzy-symbolic scaffolding methods.
The study investigated whether constrained prompts improve player experience in a voice-based detective game using GPT-4o, finding no reliable experiential differences and revealing that scaffolding effects were role-dependent, with the Interviewer gaining stability but suspect NPCs losing believability.
Large Language Models (LLMs) promise to transform interactive games by enabling non-player characters (NPCs) to sustain unscripted dialogue. Yet it remains unclear whether constrained prompts actually improve player experience. We investigate this question through The Interview, a voice-based detective game powered by GPT-4o. A within-subjects usability study ($N=10$) compared high-constraint (HCP) and low-constraint (LCP) prompts, revealing no reliable experiential differences beyond sensitivity to technical breakdowns. Guided by these findings, we redesigned the HCP into a hybrid JSON+RAG scaffold and conducted a synthetic evaluation with an LLM judge, positioned as an early-stage complement to usability testing. Results uncovered a novel pattern: scaffolding effects were role-dependent: the Interviewer (quest-giver NPC) gained stability, while suspect NPCs lost improvisational believability. These findings overturn the assumption that tighter constraints inherently enhance play. Extending fuzzy-symbolic scaffolding, we introduce \textit{Symbolically Scaffolded Play}, a framework in which symbolic structures are expressed as fuzzy, numerical boundaries that stabilize coherence where needed while preserving improvisation where surprise sustains engagement.