CAPO improves LLM calibration by up to 15% while matching or exceeding GRPO accuracy through logistic AUC loss and noise masking, enabling better abstention and scaling performance.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
Simulations show CMA-ES outperforms Nelder-Mead and other algorithms for quantum device calibration across low- and high-dimensional regimes.
citing papers explorer
-
Calibration-Aware Policy Optimization for Reasoning LLMs
CAPO improves LLM calibration by up to 15% while matching or exceeding GRPO accuracy through logistic AUC loss and noise masking, enabling better abstention and scaling performance.
-
Benchmarking Optimization Algorithms for Automated Calibration of Quantum Devices
Simulations show CMA-ES outperforms Nelder-Mead and other algorithms for quantum device calibration across low- and high-dimensional regimes.