Skip to content
View original post on X: PerplexityOfficial
Published
42/100

Perplexity's JOLT matches GRPO accuracy on MATH with 6.5x fewer tokens

AIPerplexity researchers developed JOLT, a post-training method in which one model serves as both teacher and student, with the teacher trained to give feedback the student can use. On MATH, JOLT matched GRPO's accuracy while using 6.5x fewer training tokens.
PerplexityVerified on XOfficial
@perplexity_ai
View on X

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

Source details

Perplexity · x.comPublished

Original title: New research: We developed JOLT, a post-training method where one model acts as both teacher and student, with the teacher trained to giv...

Topics

ReasoningData & trainingPapers & research