Saved in:
Bibliographic Details
Main Authors: Zekri, Oussama, Boullé, Nicolas
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2502.01384
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • 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 at https://github.com/ozekri/SEPO.