arXiv · 2024 · Preprint

Online DPO: Online Direct Preference Optimization with Fast-Slow Chasing

Biqing Qi, Pengfei Li, Fangyuan Li, Junqi Gao, K Zhang, Bowen Zhou

PDF from arXiv.HTML · PDF · Open in a new tab ↗ · Close

Date: 2024-06-08
Citations: 45
arXiv: 2406.05534 ↗

Cite

@misc{qi2024online,
  title = {Online DPO: Online Direct Preference Optimization with Fast-Slow Chasing},
  author = {Biqing Qi and Pengfei Li and Fangyuan Li and Junqi Gao and K Zhang and Bowen Zhou},
  year = {2024},
  eprint = {2406.05534},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2406.05534},
}