A Markov-copula model of LLM confidence scores enables continuous optimization of cascade thresholds, improving the area under the error-cost curve by about 4-7% over Bayesian optimization and grid search.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
ACCEPT 1representative citing papers
citing papers explorer
-
Rational Tuning of LLM Cascades via Probabilistic Modeling
A Markov-copula model of LLM confidence scores enables continuous optimization of cascade thresholds, improving the area under the error-cost curve by about 4-7% over Bayesian optimization and grid search.