Two Minds Better Than One: Collaborative Reward Modeling for LLM Alignment

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Zhang, Jiazheng, Jing, Wenqing, Zhang, Zizhuo, Xi, Zhiheng, Dou, Shihan, Weng, Rongxiang, Li, Jiahuan, Wang, Jingang, Chai, Mingxu, Hong, Shibo, Gui, Tao, Zhang, Qi
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866913843903463424
author Zhang, Jiazheng
Jing, Wenqing
Zhang, Zizhuo
Xi, Zhiheng
Dou, Shihan
Weng, Rongxiang
Li, Jiahuan
Wang, Jingang
Chai, Mingxu
Hong, Shibo
Gui, Tao
Zhang, Qi
author_facet Zhang, Jiazheng
Jing, Wenqing
Zhang, Zizhuo
Xi, Zhiheng
Dou, Shihan
Weng, Rongxiang
Li, Jiahuan
Wang, Jingang
Chai, Mingxu
Hong, Shibo
Gui, Tao
Zhang, Qi
contents Reward models (RMs) play a pivotal role in aligning large language models (LLMs) with human values. However, noisy preferences in human feedback can lead to reward misgeneralization - a phenomenon where reward models learn spurious correlations or overfit to noisy preferences, which poses important challenges to the generalization of RMs. This paper systematically analyzes the characteristics of preference pairs and aims to identify how noisy preferences differ from human-aligned preferences in reward modeling. Our analysis reveals that noisy preferences are difficult for RMs to fit, as they cause sharp training fluctuations and irregular gradient updates. These distinctive dynamics suggest the feasibility of identifying and excluding such noisy preferences. Empirical studies demonstrate that policy LLM optimized with a reward model trained on the full preference dataset, which includes substantial noise, performs worse than the one trained on a subset of exclusively high quality preferences. To address this challenge, we propose an online Collaborative Reward Modeling (CRM) framework to achieve robust preference learning through peer review and curriculum learning. In particular, CRM maintains two RMs that collaboratively filter potential noisy preferences by peer-reviewing each other's data selections. Curriculum learning synchronizes the capabilities of two models, mitigating excessive disparities to promote the utility of peer review. Extensive experiments demonstrate that CRM significantly enhances RM generalization, with up to 9.94 points improvement on RewardBench under an extreme 40\% noise. Moreover, CRM can seamlessly extend to implicit-reward alignment methods, offering a robust and versatile alignment strategy.
format Preprint
id arxiv_https___arxiv_org_abs_2505_10597
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Two Minds Better Than One: Collaborative Reward Modeling for LLM Alignment
Zhang, Jiazheng
Jing, Wenqing
Zhang, Zizhuo
Xi, Zhiheng
Dou, Shihan
Weng, Rongxiang
Li, Jiahuan
Wang, Jingang
Chai, Mingxu
Hong, Shibo
Gui, Tao
Zhang, Qi
Machine Learning
Artificial Intelligence
Computation and Language
Reward models (RMs) play a pivotal role in aligning large language models (LLMs) with human values. However, noisy preferences in human feedback can lead to reward misgeneralization - a phenomenon where reward models learn spurious correlations or overfit to noisy preferences, which poses important challenges to the generalization of RMs. This paper systematically analyzes the characteristics of preference pairs and aims to identify how noisy preferences differ from human-aligned preferences in reward modeling. Our analysis reveals that noisy preferences are difficult for RMs to fit, as they cause sharp training fluctuations and irregular gradient updates. These distinctive dynamics suggest the feasibility of identifying and excluding such noisy preferences. Empirical studies demonstrate that policy LLM optimized with a reward model trained on the full preference dataset, which includes substantial noise, performs worse than the one trained on a subset of exclusively high quality preferences. To address this challenge, we propose an online Collaborative Reward Modeling (CRM) framework to achieve robust preference learning through peer review and curriculum learning. In particular, CRM maintains two RMs that collaboratively filter potential noisy preferences by peer-reviewing each other's data selections. Curriculum learning synchronizes the capabilities of two models, mitigating excessive disparities to promote the utility of peer review. Extensive experiments demonstrate that CRM significantly enhances RM generalization, with up to 9.94 points improvement on RewardBench under an extreme 40\% noise. Moreover, CRM can seamlessly extend to implicit-reward alignment methods, offering a robust and versatile alignment strategy.
title Two Minds Better Than One: Collaborative Reward Modeling for LLM Alignment
topic Machine Learning
Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2505.10597