1
STAPO: Stabilizing Reinforcement Learning for LLMs by Silencing Rare Spurious Tokens
一种名为STAPO的新方法通过静默罕见虚假token来稳定LLM的强化学习训练，显著提升模型输出质量与收敛效率。
arXiv:2602.15620v5 Announce Type: replace-cross Abstract: Reinforcement Learning (RL) has significantly improved large language model reasoning, but e…