用八字理论构建虚拟角色推理数据集，提升AI角色的时空连贯性。
BaZi-Based Character Simulation Benchmark: Evaluating AI on Temporal and Persona Reasoning
- 结合八字符号推理与大模型生成动态角色人格
- 相比主流模型准确率提升30.3%-62.6%
- 适合对文化逻辑和角色一致性有要求的开发者
人类般的虚拟角色在游戏、叙事和虚拟现实中至关重要，但现有方法高度依赖标注数据或手工设计的角色设定，难以扩展且生成的人格缺乏真实感与上下文一致性。本文首次构建基于八字理论的角色推理问答数据集，将真实人生经历（财富、健康、家庭、事业、人际关系）转化为生命事件问题与答案。同时提出首个融合符号推理与大语言模型的BaZi-LLM系统，可生成具有时间演化特征和精细粒度的角色人格。实验表明，相较于DeepSeek-v3和GPT-5-mini等主流模型，本方法准确率提升30.3%至62.6%。当输入错误的八字信息时，模型准确率下降20%至45%，验证了文化根基的符号-大模型融合在真实角色模拟中的潜力。
原文摘要 · Abstract (English)
Human-like virtual characters are crucial for games, storytelling, and virtual reality, yet current methods rely heavily on annotated data or handcrafted persona prompts, making it difficult to scale up and generate realistic, contextually coherent personas. We create the first QA dataset for BaZi-based persona reasoning, where real human experiences categorized into wealth, health, kinship, career, and relationships are represented as life-event questions and answers. Furthermore, we propose the first BaZi-LLM system that integrates symbolic reasoning with large language models to generate temporally dynamic and fine-grained virtual personas. Compared with mainstream LLMs such as DeepSeek-v3 and GPT-5-mini, our method achieves a 30.3%-62.6% accuracy improvement. In addition, when incorrect BaZi information is used, our model's accuracy drops by 20%-45%, showing the potential of culturally grounded symbolic-LLM integration for realistic character simulation.
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。