Symbolically Scaffolded Play: Designing Role-Sensitive Prompts for Generative NPC Dialogue

📅 2025-10-29
📈 Citations: 0
Influential: 0
📄 PDF

career value

163K/year
🤖 AI Summary
This study investigates how prompt constraint strength (high vs. low) affects non-scripted NPC dialogue experiences in LLM-driven games. To address the trade-off between coherence and improvisational expressiveness, we propose the “Symbolic Scaffolding Game” framework, which employs boundary-blurring symbolic design to generate role-sensitive prompts—challenging the prevailing assumption that stronger constraints inherently yield superior outcomes. Integrating GPT-4o, JSON-structured prompting, and RAG, we conduct empirical evaluation within a voice-based detective game, employing both LLM-based adjudication for synthetic assessment and within-subject usability testing. Results reveal role-dependent constraint effects: high constraint improves behavioral stability for task-giving NPCs (e.g., investigators) but significantly degrades conversational naturalness for suspect NPCs. This validates the efficacy and necessity of role-adaptive scaffolding mechanisms in generative NPC dialogue systems.

Technology Category

Application Category

📝 Abstract
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 extit{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.
Problem

Research questions and friction points this paper is trying to address.

Investigating whether constrained prompts improve player experience in games
Evaluating role-dependent effects of symbolic scaffolding on NPC dialogue
Developing fuzzy-symbolic framework to balance NPC coherence and improvisation
Innovation

Methods, ideas, or system contributions that make the work stand out.

Hybrid JSON+RAG scaffold for NPC dialogue
Fuzzy-symbolic framework balancing coherence and improvisation
Role-dependent prompt constraints for generative characters