Adaptive Querying with AI Persona Priors

TL;DR

This paper presents a scalable Bayesian adaptive querying method using AI persona priors, improving predictions and interpretability in high-dimensional, heterogeneous settings.

Contribution

It introduces a persona-induced latent variable model that enables efficient, closed-form Bayesian updates for adaptive querying with large language models.

Findings

Persona-based posteriors provide accurate probabilistic predictions.

The method enables scalable Bayesian design for sequential item selection.

Experiments demonstrate effectiveness on synthetic data and WorldValuesBench.

Abstract

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.