Ryan Park, Rafael Rafailov, Stefano Ermon, Chelsea Finn. Disentangling Length from Quality in Direct Preference Optimization. In Lun-Wei Ku, Andre Martins, Vivek Srikumar, editors, Findings of the Association for Computational Linguistics, ACL 2024, Bangkok, Thailand and virtual meeting, August 11-16, 2024. pages 4998-5017, Association for Computational Linguistics, 2024. [doi]
@inproceedings{ParkREF24,
title = {Disentangling Length from Quality in Direct Preference Optimization},
author = {Ryan Park and Rafael Rafailov and Stefano Ermon and Chelsea Finn},
year = {2024},
url = {https://aclanthology.org/2024.findings-acl.297},
researchr = {https://researchr.org/publication/ParkREF24},
cites = {0},
citedby = {0},
pages = {4998-5017},
booktitle = {Findings of the Association for Computational Linguistics, ACL 2024, Bangkok, Thailand and virtual meeting, August 11-16, 2024},
editor = {Lun-Wei Ku and Andre Martins and Vivek Srikumar},
publisher = {Association for Computational Linguistics},
isbn = {979-8-89176-099-8},
}