[论文学习]SCoRe：通过强化学习让LLM学会自我纠正资料 论文：[2409.12917] Training Language Models to Self-Correct via Reinforcement Learning 简介​

[论文学习]S²R：通过强化学习教会 LLM 自我验证和自我修正资料 论文：[2502.12853] S$^2$R: Teaching LLMs to Self-verify and Self-correct via Reinforceme