Adaptive Querying with AI Persona Priors
For researchers in adaptive testing and Bayesian design, this work offers a scalable and interpretable alternative to classical methods, particularly in cold-start and high-dimensional settings.
The paper introduces a persona-induced latent variable model for adaptive querying that uses AI personas as priors, enabling scalable Bayesian design with closed-form updates. Experiments show accurate probabilistic predictions and an interpretable adaptive elicitation pipeline.
We study adaptive querying for learning user-dependent quantities of interest, such as responses to held-out items and psychometric indicators, within tight question 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.