On the Primacy Bias in RLVR Training
It is found that although hard problems lead to modest gains overall, they are actually the ones that help most in expanding the model's reasoning capabilities and pushing the representations, which helps to better understand some of the prior conflicting observations about RLVR.
Phuc Minh Nguyen, Ngoc-Hieu Nguyen, P. Shojaee et al.
· 0 citations