AI Paper Atlas

Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes

Adaptive Querying with AI Persona Priors

Kaizheng Wang, Yuhang Wu, assaf zeevi

ICML 2026 · Probabilistic and scientific modeling › Uncertainty and Gaussian processes · approach: Nonparametric and PAC-Bayes Bayesian learning · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use persona-based greedy querying instead of CAT-GRMgreedy persona model · WorldValuesBench real users (T=5)log loss: 1.074 -> 1.019Improved
use persona-based greedy querying instead of CAT-GRMgreedy persona model · Synthetic users (T=5)log loss: 1.207 -> 1.089Improved
use greedy instead of random question selectionpersona model · Synthetic users (T=5)log loss: 1.115 -> 1.089Improved
use non-adaptive design instead of greedy at larger budgetpersona model · WorldValuesBench real users (T=20)log loss: .999 -> .977Improved
use greedy instead of nonadaptive at small budgetpersona model · WorldValuesBench real users (T=5)log loss: 1.039 -> 1.019Improved
use multidimensional IRT (MGRM) instead of unidimensional GRMCAT baseline · Synthetic users (T=5)log loss: 1.207 -> 1.164Improved
cluster persona dictionary to 50 personas (ablation)nonadaptive persona model · WorldValuesBench real users (T=20, 10k users)log loss: .962 -> .977Hurt
cluster persona dictionary to 200 personas (ablation)nonadaptive persona model · WorldValuesBench real users (T=20, 10k users)log loss: .962 -> .963No clear effect
replace elicited distributions with deterministic answer plus noise eps=0.1 (ablation)nonadaptive persona model · WorldValuesBench real users (T=20, 10k users)log loss: .962 -> 1.291Hurt
replace elicited distributions with deterministic answer plus noise eps=0.3 (ablation)nonadaptive persona model · WorldValuesBench real users (T=20, 10k users)log loss: .962 -> 1.106Hurt
sharpen LLM distributions with temperature 0.5 (ablation)nonadaptive persona model · WorldValuesBench real users (T=20, 10k users)log loss: .962 -> 1.021Hurt
soften LLM distributions with temperature 2 (ablation)nonadaptive persona model · WorldValuesBench real users (T=20, 10k users)log loss: .962 -> 1.074Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy