Showing cs.LGShow all
3 papers · 1 filter
cs.LG2025
ShiQ: Bringing back Bellman to LLMs
Pierre Clavier, Nathan Grinsztajn, Raphael Avalos +8
The fine-tuning of pre-trained large language models (LLMs) using reinforcement learning (RL) is generally formulated as direct policy optimization. This approach was naturally fav…
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…
cs.LG2024
Understanding the performance gap between online and offline alignment algorithms
Yunhao Tang, Daniel Zhaohan Guo, Zeyu Zheng +8
Reinforcement learning from human feedback (RLHF) is the canonical framework for large language model alignment. However, rising popularity in offline alignment algorithms challeng…