LLM-elicited conditional probabilities can serve as expert-style priors for Bayesian network parameterization, and blending them with data beats both uniform priors and data-only estimation in low-data regimes.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Extracting Probabilistic Knowledge from Large Language Models for Bayesian Network Parameterization
LLM-elicited conditional probabilities can serve as expert-style priors for Bayesian network parameterization, and blending them with data beats both uniform priors and data-only estimation in low-data regimes.