Perplexity 发布 JOLT 后训练方法
New research: We developed JOLT, a post-training method where one model acts as both teacher and student, with the teacher trained to give feedback the student
AI 导读
Perplexity 公布新研究 JOLT：一种后训练方法，让同一个模型同时充当教师和学生，教师被训练为给出学生可用的反馈。在 MATH 上，它以 6.5 倍更少的训练 token 达到与 GRPO 相当的准确率。
正文
当前显示原文，中文全文译文尚未就绪。
New research: We developed JOLT, a post-training method where one model acts as both teacher and student, with the teacher trained to give feedback the student can use.
On MATH, it matched GRPO's accuracy with 6.5x fewer training tokens.