3 papers
cs.LG2026
A Layer-wise Analysis of Supervised Fine-Tuning
Qinghua Zhao, Xueling Gong, Xinyu Chen +2
While critical for alignment, Supervised Fine-Tuning (SFT) incurs the risk of catastrophic forgetting, yet the layer-wise emergence of instruction-following capabilities remains el…
cs.LG2026
Segmental Advantage Estimation: Enhancing PPO for Long-Context LLM Training
Xue Gong, Qi Yi, Ziyuan Nan +8
Training Large Language Models (LLMs) for reasoning tasks is increasingly driven by Reinforcement Learning with Verifiable Rewards (RLVR), where Proximal Policy Optimization (PPO)…
cs.LG2025
Low-probability Tokens Sustain Exploration in Reinforcement Learning with Verifiable Reward
Guanhua Huang, Tingqiang Xu, Mingze Wang +7
Reinforcement Learning with Verifiable Rewards (RLVR) has propelled Large Language Models in complex reasoning, yet its scalability is often hindered by a training bottleneck where…