Balancing Rewards in Text Summarization: Multi-Objective Reinforcement Learning via HyperVolume Optimization

TL;DR

This paper introduces hypervolume optimization for reinforcement learning in text summarization, enabling models to generate more balanced summaries across multiple objectives such as relevance, coherence, and fluency.

Contribution

It proposes a novel hypervolume-based RL strategy that dynamically balances multiple summarization objectives, improving overall performance and diversity of summaries.

Findings

Outperforms group relative policy optimization (GRPO) in multiple datasets

A 7B foundation model with HVO matches GPT-4's performance in summarization

Produces more balanced summaries with shorter generation lengths

Abstract

Text summarization is a crucial task that requires the simultaneous optimization of multiple objectives, including consistency, coherence, relevance, and fluency, which presents considerable challenges. Although large language models (LLMs) have demonstrated remarkable performance, enhanced by reinforcement learning (RL), few studies have focused on optimizing the multi-objective problem of summarization through RL based on LLMs. In this paper, we introduce hypervolume optimization (HVO), a novel optimization strategy that dynamically adjusts the scores between groups during the reward process in RL by using the hypervolume method. This method guides the model's optimization to progressively approximate the pareto front, thereby generating balanced summaries across multiple objectives. Experimental results on several representative summarization datasets demonstrate that our method outperforms group relative policy optimization (GRPO) in overall scores and shows more balanced performance across different dimensions. Moreover, a 7B foundation model enhanced by HVO performs comparably to GPT-4 in the summarization task, while maintaining a shorter generation length. Our code is publicly available at https://github.com/ai4business-LiAuto/HVO.git