A persona-induced latent variable model with LLM response distributions enables closed-form Bayesian updates and finite-mixture predictions for scalable adaptive querying of user-dependent quantities.
Advances in Neural Information Processing Systems , volume=
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Adaptive Querying with AI Persona Priors
A persona-induced latent variable model with LLM response distributions enables closed-form Bayesian updates and finite-mixture predictions for scalable adaptive querying of user-dependent quantities.