DVPO learns token-level value distributions and uses asymmetric risk regularization to contract lower tails while expanding upper tails, outperforming PPO and GRPO under noisy supervision in dialogue, math, and QA tasks.
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
UNVERDICTED 1representative citing papers
citing papers explorer
-
DVPO: Distributional Value Modeling-based Policy Optimization for LLM Post-Training
DVPO learns token-level value distributions and uses asymmetric risk regularization to contract lower tails while expanding upper tails, outperforming PPO and GRPO under noisy supervision in dialogue, math, and QA tasks.