4 papers · 1 filter
Self-Improving Robust Preference Optimization
Eugene Choi, Arash Ahmadian, Matthieu Geist +2
Online and offline RLHF methods, such as PPO and DPO, have been highly successful in aligning AI with human preferences. Despite their success, however, these methods suffer from f…
Contrastive Policy Gradient: Aligning LLMs on sequence-level scores in a supervised-friendly fashion
Yannis Flet-Berliac, Nathan Grinsztajn, Florian Strub +8
Reinforcement Learning (RL) has been used to finetune Large Language Models (LLMs) using a reward model trained from preference data, to better align with human judgment. The recen…
Imitating Language via Scalable Inverse Reinforcement Learning
Markus Wulfmeier, Michael Bloesch, Nino Vieillard +13
The majority of language model training builds on imitation learning. It covers pretraining, supervised fine-tuning, and affects the starting conditions for reinforcement learning…
Averaging log-likelihoods in direct alignment
Nathan Grinsztajn, Yannis Flet-Berliac, Mohammad Gheshlaghi Azar +8
To better align Large Language Models (LLMs) with human judgment, Reinforcement Learning from Human Feedback (RLHF) learns a reward model and then optimizes it using regularized RL…