BY571/SCoRe

SCoRe: Training Language Models to Self-Correct via Reinforcement Learning

⭐ 16 ⑂ 0 Python · 2026-05-15推送

fine-tuning language-model reinforcement-learning self-correction

16

Watchers

0

贡献者

0

Commits

0

Releases

0

Open Issues

2026-05-15

最近推送

原文中文

暂无 README