2 papers
cs.CL2024
West-of-N: Synthetic Preferences for Self-Improving Reward Models
Alizée Pace, Jonathan Mallinson, Eric Malmi +2
The success of reinforcement learning from human feedback (RLHF) in language model alignment is strongly dependent on the quality of the underlying reward model. In this paper, we…
cs.LG2024
Offline Regularised Reinforcement Learning for Large Language Models Alignment
Pierre Harvey Richemond, Yunhao Tang, Daniel Guo +15
The dominant framework for alignment of large language models (LLM), whether through reinforcement learning from human feedback or direct preference optimisation, is to learn from…