Identifies two gaps in entropy-based uncertainty for LLM post-training and proposes GCPO to align geometry-aware disagreement measures with reward-based calibration for better gradient regulation.
Ratio-variance regularized policy optimization for efficient llm fine-tuning.arXiv preprint arXiv:2601.03320, 2026
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Why Semantic Entropy Fails: Geometry-Aware and Calibrated Uncertainty for Policy Optimization
Identifies two gaps in entropy-based uncertainty for LLM post-training and proposes GCPO to align geometry-aware disagreement measures with reward-based calibration for better gradient regulation.