Perplexity 与 NVIDIA 提出 JOLT 自蒸馏训练法
Perplexity 与 NVIDIA AI 提出后训练方法 JOLT,让同一模型同时充当教师与学生,并训练教师依据自身尝试的奖励学习、惩罚偏离学生行为的漂移。在 MATH 基准上,JOLT 以少 6.5 倍的训练 token 达到与 GRPO 相当的准确率;JOLT+ 额外给学生模型结果奖励,在数学、编程、终端任务和工具使用基准上明显优于 GRPO。
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