Perplexity· @perplexity_ai · X·· 3 小时前AI 评分38
AI 导读
新研究：我们开发了 JOLT，一种后训练方法，让一个模型同时充当教师和学生，其中教师经过训练，能够给出学生可用的反馈。 在 MATH 上，它以少 6.5 倍的训练 token 达到了与 GRPO 相当的准确率。 https://www.perplexity.ai/hub/blog/a-good-teacher-meets-the-student-where-they-are
正文 · 原文
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.
https://www.perplexity.ai/hub/blog/a-good-teacher-meets-the-student-where-they-are
来源：Perplexity · x.com