Discrete diffusion models have recently gained significant attention due to their ability to process complex discrete structures for language modeling. However, fine-tuning these models with policy gradient methods, as is commonly done in Reinforcement Learning from Human Feedback (RLHF), remains a challenging task. We propose an efficient, broadly applicable, and theoretically justified policy gradient algorithm, called Score Entropy Policy Optimization (SEPO), for fine-tuning discrete diffusion models over non-differentiable rewards. Our numerical experiments across several discrete generative tasks demonstrate the scalability and efficiency of our method. Our code is available atthis https URL
View on arXiv@article{zekri2025_2502.01384,
title={ Fine-Tuning Discrete Diffusion Models with Policy Gradient Methods },
author={ Oussama Zekri and Nicolas Boullé },
journal={arXiv preprint arXiv:2502.01384},
year={ 2025 }
}