CurveRL derives a quantile-coordinate reweighting rule from a utility functional on pass rates and shows it outperforms GRPO on reasoning benchmarks.
arXiv preprint arXiv:2410.02504 , year=
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
background 2
method 1
citation-polarity summary
years
2026 6representative citing papers
MASS-DPO derives a Plackett-Luce-specific log-determinant Fisher information objective to select non-redundant negative samples, matching or exceeding multi-negative DPO performance with substantially fewer negatives across four benchmarks and three model families.
A learnable continuous perturbation framework for LLM token prefixes via latent vector transformations, optimized through unbiased estimating equations, yields gains in out-of-domain performance.
RLAVR uses the Corrective Advantage Gap metric and CARE policy to actively acquire ground-truth labels for key samples, stabilizing RLVR training and boosting performance with limited annotation budgets.
Perturbing the prefix before next-token prediction, during both training and inference, improves out-of-distribution language-model generation and yields a conditional extrapolation guarantee.
A statistical survey of RLHF for LLM alignment that connects preference learning and policy optimization to models like Bradley-Terry-Luce while reviewing methods, extensions, and open challenges.
citing papers explorer
-
CurveRL: Principled Distribution-Aware Context Reweighting for LLM Reasoning
CurveRL derives a quantile-coordinate reweighting rule from a utility functional on pass rates and shows it outperforms GRPO on reasoning benchmarks.
-
MASS-DPO: Multi-negative Active Sample Selection for Direct Policy Optimization
MASS-DPO derives a Plackett-Luce-specific log-determinant Fisher information objective to select non-redundant negative samples, matching or exceeding multi-negative DPO performance with substantially fewer negatives across four benchmarks and three model families.
-
Learning Perturbations to Extrapolate Your LLM
A learnable continuous perturbation framework for LLM token prefixes via latent vector transformations, optimized through unbiased estimating equations, yields gains in out-of-domain performance.
-
When Self-Belief Misleads: Active Label Acquisition for Reinforcement Learning with Verifiable Rewards
RLAVR uses the Corrective Advantage Gap metric and CARE policy to actively acquire ground-truth labels for key samples, stabilizing RLVR training and boosting performance with limited annotation budgets.
-
Perturbation is All You Need for Extrapolating Language Models
Perturbing the prefix before next-token prediction, during both training and inference, improves out-of-distribution language-model generation and yields a conditional extrapolation guarantee.
-
Reinforcement Learning from Human Feedback: A Statistical Perspective
A statistical survey of RLHF for LLM alignment that connects preference learning and policy optimization to models like Bradley-Terry-Luce while reviewing methods, extensions, and open challenges.