用符号化框架提升游戏对话角色的稳定性与真实感
Symbolically Scaffolded Play: Designing Role-Sensitive Prompts for Generative NPC Dialogue
- 将角色提示设计为混合结构，结合JSON格式与检索增强生成
- 角色类型不同，约束效果相反：审问者更稳定，嫌疑人失真实感
- 提出模糊符号化支架新框架，平衡控制与即兴创造力
大型语言模型（LLMs）有望通过非脚本化对话革新互动游戏中的非玩家角色（NPC）。然而，受限提示是否真能提升玩家体验尚不明确。我们通过基于GPT-4o的语音推理侦探游戏《The Interview》开展内部对照可用性研究（N=10），对比高约束（HCP）与低约束（LCP）提示，发现除对技术故障敏感外，体验无显著差异。基于此，我们将HCP重构为混合式JSON+RAG架构，并借助大模型评判进行合成评估，作为可用性测试的早期补充。结果揭示新模式：支架效应具角色依赖性——审问者（任务发布者NPC）表现更稳定，而嫌疑人NPC则丧失即兴可信度。该发现推翻了‘约束越紧越优’的假设。我们进一步提出‘符号化支架游戏’（Symbolically Scaffolded Play）框架，以模糊数值边界表达符号结构，在必要处保障连贯性，同时保留惊喜带来的沉浸感。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。