New research: We developed JOLT, a post-training method where one model acts as both teacher and student, with the teacher trained to giv...
摘要
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，教师经过训练以提供学生可用的反馈。 在 MATH 上，它以少 6.5 倍的训练 token 达到了与 GRPO 相同的准确率。 https://www.perplexity.ai/hub/blog/a-good-teacher-meets-the-student-where-they-are
摘要由模型根据原文撰写，以原文为准。
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
引用原文
perplexity_ai. New research: We developed JOLT, a post-training method where one model acts as both teacher and student, with the teacher trained to giv...[EB/OL]. (2026-10-22)[访问日期]. https://x.com/perplexity_ai/status/2112978260808376411.