用AI人格模型实现高效用户偏好预测，节省查询次数。
Adaptive Querying with AI Persona Priors
- 将用户映射为预设AI人格，构建可解析的先验分布
- 在有限查询下，对冷启动用户实现高精度概率预测
- 适合需要快速理解用户偏好的推荐与测评系统
我们研究在严格查询预算下，学习用户依赖性量值（如未见项目响应、心理测量指标）的自适应查询问题。传统贝叶斯设计与计算机化自适应测试通常依赖强参数假设或昂贵的后验近似，在异质性、高维及冷启动场景中受限。本文提出一种人格诱导的隐变量模型，通过有限人格字典表征用户状态，每种人格由大语言模型生成响应分布。该模型提供表达性强的先验，支持闭式后验更新与高效有限混合预测，实现可扩展的贝叶斯序列选题设计。在合成数据和WorldValuesBench上的实验表明，基于人格的后验能实现准确的概率预测，并提供可解释的自适应采集流程。
原文摘要 · Abstract (English)
We study adaptive querying for learning user-dependent quantities of interest, such as responses to held-out items and psychometric indicators, within tight query budgets. Classical Bayesian design and computerized adaptive testing typically rely on restrictive parametric assumptions or expensive posterior approximations, limiting their use in heterogeneous, high-dimensional, and cold-start settings. We introduce a persona-induced latent variable model that represents a user's state through membership in a finite dictionary of AI personas, each offering response distributions produced by a large language model. This yields expressive priors with closed-form posterior updates and efficient finite-mixture predictions, enabling scalable Bayesian design for sequential item selection. Experiments on synthetic data and WorldValuesBench demonstrate that persona-based posteriors deliver accurate probabilistic predictions and an interpretable adaptive elicitation pipeline.
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。