Changyu Chen, Zichen Liu, Chao Du, Tianyu Pang, Qian Liu 0012, Arunesh Sinha, Pradeep Varakantham, Min Lin. Bootstrapping Language Models with DPO Implicit Rewards. In The Thirteenth International Conference on Learning Representations, ICLR 2025, Singapore, April 24-28, 2025. OpenReview.net, 2025. [doi]
@inproceedings{ChenLDPLSVL25,
title = {Bootstrapping Language Models with DPO Implicit Rewards},
author = {Changyu Chen and Zichen Liu and Chao Du and Tianyu Pang and Qian Liu 0012 and Arunesh Sinha and Pradeep Varakantham and Min Lin},
year = {2025},
url = {https://openreview.net/forum?id=dliIIodM6b},
researchr = {https://researchr.org/publication/ChenLDPLSVL25},
cites = {0},
citedby = {0},
booktitle = {The Thirteenth International Conference on Learning Representations, ICLR 2025, Singapore, April 24-28, 2025},
publisher = {OpenReview.net},
}