6 papers
CoCA: Criterion-Aware Credit Assignment for Rubric-Based Reinforcement Learning
Guangcheng Zhu, Yingfan Ma, Xing Zheng +7
Rubric-based reinforcement learning (RL) evaluates responses against explicit criteria to construct rewards, offering a viable way to train large language models on open-ended task…
PreSO: Privileged Representation Isolation for On-Policy Self-Distillation
Yuhang Yang, Mingxuan Xia, Chao Ye +6
On-policy self-distillation (OPSD) uses a self-teacher conditioned on privileged information to turn the sparse outcome signal of reinforcement learning with verifiable rewards (RL…
DE-Venus: A Data-Efficient RLVR Framework for Large Language Models
Shenzhi Yang, Guangcheng Zhu, Kai Tang +11
Reinforcement learning with verifiable rewards (RLVR) improves large language model reasoning, but its practical scaling is constrained by expensive on-policy rollouts and the cost…
GeoMin: Data-Efficient Semi-Supervised RLVR via Geometric Distribution Modeling
Guangcheng Zhu, Shenzhi Yang, Haobo Wang +9
Reinforcement learning with verifiable rewards (RLVR) significantly advances LLM reasoning, yet it faces a dilemma: standard supervised scaling is throttled by high annotation cost…
A Syllogistic Probe: Tracing the Evolution of Logic Reasoning in Large Language Models
Zhengqing Zang, Yuqi Ding, Yanmei Gu +5
Human logic has gradually shifted from intuition-driven inference to rigorous formal systems. Motivated by recent advances in large language models (LLMs), we explore whether LLMs…
Parallelism and Generation Order in Masked Diffusion Language Models: Limits Today, Potential Tomorrow
Yangyang Zhong, Yanmei Gu, Zhengqing Zang +14
Masked Diffusion Language Models (MDLMs) promise parallel token generation and arbitrary-order decoding, yet it remains unclear to what extent current models truly realize these ca…