Gradient-Adaptive Policy Optimization: Towards Multi-Objective Alignment of Large Language Models

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Li, Chengao, Zhang, Hanyu, Xu, Yunkun, Xue, Hongyan, Ao, Xiang, He, Qing
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866911035392262144
author Li, Chengao
Zhang, Hanyu
Xu, Yunkun
Xue, Hongyan
Ao, Xiang
He, Qing
author_facet Li, Chengao
Zhang, Hanyu
Xu, Yunkun
Xue, Hongyan
Ao, Xiang
He, Qing
contents Reinforcement Learning from Human Feedback (RLHF) has emerged as a powerful technique for aligning large language models (LLMs) with human preferences. However, effectively aligning LLMs with diverse human preferences remains a significant challenge, particularly when they are conflict. To address this issue, we frame human value alignment as a multi-objective optimization problem, aiming to maximize a set of potentially conflicting objectives. We introduce Gradient-Adaptive Policy Optimization (GAPO), a novel fine-tuning paradigm that employs multiple-gradient descent to align LLMs with diverse preference distributions. GAPO adaptively rescales the gradients for each objective to determine an update direction that optimally balances the trade-offs between objectives. Additionally, we introduce P-GAPO, which incorporates user preferences across different objectives and achieves Pareto solutions that better align with the user's specific needs. Our theoretical analysis demonstrates that GAPO converges towards a Pareto optimal solution for multiple objectives. Empirical results on Mistral-7B show that GAPO outperforms current state-of-the-art methods, achieving superior performance in both helpfulness and harmlessness.
format Preprint
id arxiv_https___arxiv_org_abs_2507_01915
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Gradient-Adaptive Policy Optimization: Towards Multi-Objective Alignment of Large Language Models
Li, Chengao
Zhang, Hanyu
Xu, Yunkun
Xue, Hongyan
Ao, Xiang
He, Qing
Computation and Language
Artificial Intelligence
Machine Learning
Reinforcement Learning from Human Feedback (RLHF) has emerged as a powerful technique for aligning large language models (LLMs) with human preferences. However, effectively aligning LLMs with diverse human preferences remains a significant challenge, particularly when they are conflict. To address this issue, we frame human value alignment as a multi-objective optimization problem, aiming to maximize a set of potentially conflicting objectives. We introduce Gradient-Adaptive Policy Optimization (GAPO), a novel fine-tuning paradigm that employs multiple-gradient descent to align LLMs with diverse preference distributions. GAPO adaptively rescales the gradients for each objective to determine an update direction that optimally balances the trade-offs between objectives. Additionally, we introduce P-GAPO, which incorporates user preferences across different objectives and achieves Pareto solutions that better align with the user's specific needs. Our theoretical analysis demonstrates that GAPO converges towards a Pareto optimal solution for multiple objectives. Empirical results on Mistral-7B show that GAPO outperforms current state-of-the-art methods, achieving superior performance in both helpfulness and harmlessness.
title Gradient-Adaptive Policy Optimization: Towards Multi-Objective Alignment of Large Language Models
topic Computation and Language
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2507.01915