2025
ShiQ: Bringing back Bellman to LLMs
Pierre Clavier, Nathan Grinsztajn, Raphaël Avalos, Yannis Flet-Berliac, Irem Ergun, Omar Darwiche Domingues +4
NeurIPS 2025poster
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 favored as it efficiently improves a pretrained LLM with simple gradient updates. Another RL paradigm, Q-learning methods,…