Evan Frick, Tianle Li, Connor Chen, Wei-Lin Chiang, Anastasios Nikolas Angelopoulos, Jiantao Jiao, Banghua Zhu, Joseph E. Gonzalez, Ion Stoica. How to Evaluate Reward Models for RLHF. In The Thirteenth International Conference on Learning Representations, ICLR 2025, Singapore, April 24-28, 2025. OpenReview.net, 2025. [doi]
@inproceedings{FrickLCCAJZGS25,
title = {How to Evaluate Reward Models for RLHF},
author = {Evan Frick and Tianle Li and Connor Chen and Wei-Lin Chiang and Anastasios Nikolas Angelopoulos and Jiantao Jiao and Banghua Zhu and Joseph E. Gonzalez and Ion Stoica},
year = {2025},
url = {https://openreview.net/forum?id=cbttLtO94Q},
researchr = {https://researchr.org/publication/FrickLCCAJZGS25},
cites = {0},
citedby = {0},
booktitle = {The Thirteenth International Conference on Learning Representations, ICLR 2025, Singapore, April 24-28, 2025},
publisher = {OpenReview.net},
}