GRPO-RM: Fine-Tuning Representation Models via GRPO-Driven Reinforcement Learning
This work addresses the challenge of improving representation learning for AI applications, but it is incremental as it adapts an existing method to a new domain.
The paper tackles the problem of fine-tuning representation models by adapting the Group Relative Policy Optimization (GRPO) method from large language models, and the result shows effectiveness validated through extensive experiments on real-world datasets.
The Group Relative Policy Optimization (GRPO), a reinforcement learning method used to fine-tune large language models (LLMs), has proved its effectiveness in practical applications such as DeepSeek-R1. It raises a question whether GRPO can be generalized to representation learning models. In this paper, we propose Group Relative Policy Optimization for Representation Model (GRPO-RM), and investigate the performance of GRPO-like policy in post-training representation models. Specifically, our method establishes a predefined output set to functionally replace token sequence sampling in LLMs, thereby generating an output group, which is essential for the probability-driven optimization of GRPO. In addition, a specialized reward function is designed to accommodate the properties of representation models. Extensive experiments are conducted on various real-world datasets to validate the effectiveness of our proposed method.