Re:Does RL Incentivize Reasoning in LLMs Beyond the Base Model?
by imtringued on Tuesday April 22, 2025 @11:31AM
(#43763359)
>Our key finding is that all reasoning paths in the RLVR model are already present in the base model.
This is a really good observation. It means that you don't need to RL the full model. You merely need to RL a few LoRAs or maybe a small Mamba model appended to the final layer.
This is a really good observation. It means that you don't need to RL the full model. You merely need to RL a few LoRAs or maybe a small Mamba model appended to the final layer.