AIME 2024 contamination

#6
by autoprogrammer - opened

Why the AIME2024 is in the training data and you also report it as benchmark in your paper?

Hello, we implemented strict data decontamination strategies during both the SFT and GRPO stages, including:
1. Exact decontamination
2. Semantic decontamination

We guarantee that none of our training data contains any AIME2024 data.

Emperorizzis changed discussion status to closed

Sign up or log in to comment