DCPO decouples reasoning optimization from calibration in RLVR to fix overconfidence in LLMs without losing accuracy.
Sayself: Teaching llms to express con- fidence with self-reflective rationales.arXiv preprint arXiv:2405.20974,
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
-
Decoupling Reasoning and Confidence: Resurrecting Calibration in Reinforcement Learning from Verifiable Rewards
DCPO decouples reasoning optimization from calibration in RLVR to fix overconfidence in LLMs without losing accuracy.