基于AI人格先验的自适应查询
Adaptive Querying with AI Persona Priors
AI总结：
提出一种基于AI人格诱导的潜变量模型，利用大语言模型生成响应分布，实现高效贝叶斯设计，用于在有限查询预算下学习用户相关量。
摘要：
我们研究在严格查询预算内，通过自适应查询学习用户相关的感兴趣量（如对保留项目的响应和心理测量指标）的问题。经典的贝叶斯设计和计算机化自适应测试通常依赖于限制性的参数假设或昂贵的后验近似，限制了它们在异质性、高维和冷启动场景中的应用。我们引入了一种人格诱导的潜变量模型，通过有限字典中的AI人格成员身份来表示用户状态，每种人格由大语言模型产生的响应分布提供。这产生了具有闭式后验更新和高效有限混合预测的表达性先验，从而实现了可扩展的贝叶斯设计用于顺序项目选择。在合成数据和WorldValuesBench上的实验表明，基于人格的后验提供了准确的概率预测和可解释的自适应启发流程。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
