3 papers
cs.LG2025
Tapered Off-Policy REINFORCE: Stable and efficient reinforcement learning for LLMs
Nicolas Le Roux, Marc G. Bellemare, Jonathan Lebensold +7
We propose a new algorithm for fine-tuning large language models using reinforcement learning. Tapered Off-Policy REINFORCE (TOPR) uses an asymmetric, tapered variant of importance…
cs.LG2024
VinePPO: Refining Credit Assignment in RL Training of LLMs
Amirhossein Kazemnejad, Milad Aghajohari, Eva Portelance +4
Large language models (LLMs) are increasingly applied to complex reasoning tasks that require executing several complex steps before receiving any reward. Properly assigning credit…
cs.LG2024
Towards Modular LLMs by Building and Reusing a Library of LoRAs
Oleksiy Ostapenko, Zhan Su, Edoardo Maria Ponti +5
The growing number of parameter-efficient adaptations of a base large language model (LLM) calls for studying whether we can reuse such trained adapters to improve performance for…