RLMF uses quality of model self-judgments to refine RL rankings and select training data, achieving SOTA faithful calibration while preserving accuracy and outperforming standard RL by up to 63%.
C 2gspg: Confidence- calibrated group sequence policy gradient towards self- aware reasoning.arXiv preprint arXiv:2509.23129
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 4roles
background 1polarities
background 1representative citing papers
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.
DCPO decouples reasoning and calibration in RLVR, matching GRPO accuracy while reducing overconfidence via a claimed fundamental gradient conflict.
citing papers explorer
-
Reinforcement Learning with Metacognitive Feedback Elicits Faithful Uncertainty Expression in LLMs
RLMF uses quality of model self-judgments to refine RL rankings and select training data, achieving SOTA faithful calibration while preserving accuracy and outperforming standard RL by up to 63%.
-
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.
-
Decoupling Reasoning and Confidence: Resurrecting Calibration in Reinforcement Learning from Verifiable Rewards
DCPO decouples reasoning and calibration in RLVR, matching GRPO accuracy while reducing overconfidence via a claimed fundamental gradient conflict.
- Process Supervision of Confidence Margin for Calibrated LLM Reasoning