Back to Search Start Over

HAF-RM: A Hybrid Alignment Framework for Reward Model Training

Authors :
Liu, Shujun
Shen, Xiaoyu
Lai, Yuhang
Wang, Siyuan
Yue, Shengbin
Huang, Zengfeng
Huang, Xuanjing
Wei, Zhongyu
Publication Year :
2024

Abstract

The reward model has become increasingly important in alignment, assessment, and data construction for large language models (LLMs). Most existing researchers focus on enhancing reward models through data improvements, following the conventional training framework for reward models that directly optimizes the predicted rewards. In this paper, we propose a hybrid alignment framework HaF-RM for reward model training by introducing an additional constraint on token-level policy probabilities in addition to the reward score. It can simultaneously supervise the internal preference model at the token level and optimize the mapping layer of the reward model at the sequence level. Theoretical justifications and experiment results on five datasets show the validity and effectiveness of our proposed hybrid framework for training a high-quality reward model. By decoupling the reward modeling procedure and incorporating hybrid supervision, our HaF-RM framework offers a principled and effective approach to enhancing the performance and alignment of reward models, a critical component in the responsible development of powerful language models. We release our code at https://haf-rm.github.io.

Details

Database :
arXiv
Publication Type :
Report
Accession number :
edsarx.2407.04185
Document Type :
Working Paper