Pre-DPO: Improving Data Utilization in Direct Preference Optimization Using a Guiding Reference Model
- AAAI Conference on Artificial Intelligence
- 2025-04-22
- 9
@inproceedings{pan2025predpo,
title = {Pre-DPO: Improving Data Utilization in Direct Preference Optimization Using a Guiding Reference Model},
author = {Jun-Shu Pan and Wei Shen and Shulin Huang and Qiji Zhou and Yue Zhang},
year = {2025},
booktitle = {AAAI Conference on Artificial Intelligence},
eprint = {2504.15843},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2504.15843},
}