让游戏NPC交易更可信，避免物品幻觉和算错。
State-Inference-Based Prompting for Natural Language Trading with Game NPCs
- 用状态推断自动识别交易阶段，精准引用物品
- 97%以上交易状态合规，计算准确率达99.7%
- 适合想提升游戏非玩家角色可信度的开发者
大型语言模型虽能实现动态游戏交互，但在规则约束的交易系统中仍易出现物品幻觉和计算错误，损害玩家信任。本文提出基于状态推断的提示方法（SIBP），通过自主推断对话状态并遵循上下文规则，将交易过程分解为六个统一状态，在提示框架内实现上下文感知的物品引用与占位符定价计算。在100次交易对话上的评估显示，状态合规率超97%，物品引用准确率超95%，计算精确率达99.7%。SIBP在保持高效计算的同时优于基线方法，为商业游戏中可信的非玩家角色交互提供了实用基础。
原文摘要 · Abstract (English)
Large Language Models enable dynamic game interactions but struggle with rule-governed trading systems. Current implementations suffer from rule violations, such as item hallucinations and calculation errors, that erode player trust. Here, State-Inference-Based Prompting (SIBP) enables reliable trading through autonomous dialogue state inference and context-specific rule adherence. The approach decomposes trading into six states within a unified prompt framework, implementing context-aware item referencing and placeholder-based price calculations. Evaluation across 100 trading dialogues demonstrates >97% state compliance, >95% referencing accuracy, and 99.7% calculation precision. SIBP maintains computational efficiency while outperforming baseline approaches, establishing a practical foundation for trustworthy NPC interactions in commercial games.
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。