DASD improves math reasoning in LLMs by adaptively directing self-distillation based on per-token entropy to balance exploration and step accuracy, outperforming prior self-distillation and RLVR baselines on six benchmarks.
CoRR , volume =
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
fields
cs.LG 4years
2026 4verdicts
UNVERDICTED 4representative citing papers
Entropy polarity is a signed token-level quantity derived from a first-order approximation of entropy change that predicts whether RL updates expand or contract policy entropy in LLM fine-tuning, revealing an asymmetry between high- and low-probability tokens.
Proposes Near-boundary Stochastic Rescue (NSR) as a stochastic modification to clipping in RLVR that recovers near-boundary signals and yields gains over baselines like DAPO and GSPO.
OWPO decouples optimization direction from magnitude via asymmetric reweighting (Accelerated Alignment for inferior deviations, Gain Locking for superior) plus iterative references to create a ratchet effect for continuous LLM improvement.
citing papers explorer
-
Tailoring Teaching to Aptitude: Direction-Adaptive Self-Distillation for LLM Reasoning
DASD improves math reasoning in LLMs by adaptively directing self-distillation based on per-token entropy to balance exploration and step accuracy, outperforming prior self-distillation and RLVR baselines on six benchmarks.
-
Entropy Polarity in Reinforcement Fine-Tuning: Direction, Asymmetry, and Control
Entropy polarity is a signed token-level quantity derived from a first-order approximation of entropy change that predicts whether RL updates expand or contract policy entropy in LLM fine-tuning, revealing an asymmetry between high- and low-probability tokens.
-
Clipping Bottleneck: Stabilizing RLVR via Stochastic Recovery of Near-Boundary Signals
Proposes Near-boundary Stochastic Rescue (NSR) as a stochastic modification to clipping in RLVR that recovers near-boundary signals and yields gains over baselines like DAPO and GSPO.
-
One-Way Policy Optimization for Self-Evolving LLMs
OWPO decouples optimization direction from magnitude via asymmetric reweighting (Accelerated Alignment for inferior deviations, Gain Locking for superior) plus iterative references to create a ratchet effect for continuous LLM improvement.