Skip to content

Conversation

@codelion
Copy link
Member

Implements the paper "Re-Reading Improves Reasoning in Large Language Models" but the results on livebench are mixed:

########## All Groups ##########
category average coding data_analysis instruction_following language math reasoning
model
gpt-4o-mini-2024-07-18 44.1 42.5 42.7 65.4 33.8 44.1 36.0
re2-gpt-4o-mini-2024-07-18 43.4 40.9 46.4 68.6 35.8 42.3 26.7

@codelion codelion merged commit b9b7f95 into main Sep 21, 2024
@codelion codelion deleted the feat-implement-reread branch September 21, 2024 11:25
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

2 participants