LLM surrogate beliefs under sparse observations depend on prompts and query protocols, with structural prompts as priors, pointwise vs joint querying producing different beliefs, and sequential evidence causing non-monotonic updates that affect acquisition and regret.
Taking the human out of the loop: A review of bayesian optimization.Proceedings of the IEEE, 104(1):148–175
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
representative citing papers
NUBO is a transparent, modular Python package implementing established Bayesian optimization techniques for bounded, constrained, and mixed input spaces.
citing papers explorer
-
Elicitation Matters: How Prompts and Query Protocols Shape LLM Surrogates under Sparse Observations
LLM surrogate beliefs under sparse observations depend on prompts and query protocols, with structural prompts as priors, pointwise vs joint querying producing different beliefs, and sequential evidence causing non-monotonic updates that affect acquisition and regret.
-
NUBO: A Transparent Python Package for Bayesian Optimization
NUBO is a transparent, modular Python package implementing established Bayesian optimization techniques for bounded, constrained, and mixed input spaces.