@askalphaxiv: Your Base Model is Smarter Tha...
@askalphaxiv
10 views
Oct 25, 2025
1
Your Base Model is Smarter Than You Think
This paper proposes a way to beat the lack of generation diversity in RL without RL!
By using Markov Chain Monte Carlo’s ‘power sampling’ that reuses a base LLM’s own probabilities, it’s able to beat GRPO without training & verifiers
This paper proposes a way to beat the lack of generation diversity in RL without RL!
By using Markov Chain Monte Carlo’s ‘power sampling’ that reuses a base LLM’s own probabilities, it’s able to beat GRPO without training & verifiers
