33 citations · 38 across the 8 of their papers we have counts for
Showing 2026Show all
2 papers · 1 filter
cs.LG2026
Learning to Solve Hard Problems in RL for LLMs by Never Giving Up
Michael Noukhovitch, Hamish Ivison, Nathan Lambert +1
We demonstrate that training LLMs with RL does not improve performance equally across a dataset. RL shows large improvements on easy problems that an LLM is already good at solving…
cs.LG2026
Gradient Regularization Mitigates Reward Hacking in Reinforcement Learning from Human Feedback and Verifiable Rewards
Johannes Ackermann, Michael Noukhovitch, Takashi Ishida +1
Reinforcement Learning from Human Feedback (RLHF) or Verifiable Rewards (RLVR) are two key steps in the post-training of modern Language Models (LMs). A common problem is reward ha…