Multi-Dimensional Optimization for Text Summarization via Reinforcement Learning

2024-06-01 · Sangwon Ryu, Heejin Do, Yunsu Kim, Gary Geunbae Lee, Jungseul Ok

The evaluation of summary quality encompasses diverse dimensions such as consistency, coherence, relevance, and fluency. However, existing summarization methods often target a specific dimension, facing challenges in generating well-balanced summaries across multiple dimensions. In this paper, we propose multi-objective reinforcement learning tailored to generate balanced summaries across all four dimensions. We introduce two multi-dimensional optimization (MDO) strategies for adaptive learning: 1) MDO_min, rewarding the current lowest dimension score, and 2) MDO_pro, optimizing multiple dimensions similar to multi-task learning, resolves conflicting gradients across dimensions through gradient projection. Unlike prior ROUGE-based rewards relying on reference summaries, we use a QA-based reward model that aligns with human preferences. Further, we discover the capability to regulate the length of summaries by adjusting the discount factor, seeking the generation of concise yet informative summaries that encapsulate crucial points. Our approach achieved substantial performance gains compared to baseline models on representative summarization datasets, particularly in the overlooked dimensions.

📄 PDF Abstract BibTeX arXiv:2406.00303

Code (0)

등록된 구현이 없습니다.

Tasks

Multi-Objective Reinforcement LearningMulti-Task Learning reinforcement-learning Reinforcement Learning Text Summarization

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

2025-10-22 · Junjie Song, Yiwen Liu, Dapeng Li, Yin Sun 외 arxiv

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 la…

Reinforcement Learning Text Summarization

Dimensionality on Summarization

2015-07-01 · Hai Zhuge

Summarization is one of the key features of human intelligence. It plays an important role in understanding and representation. With rapid and continual expansion of texts, pictures and videos in cyberspace, automatic su…

Text Summarization

Robust Deep Reinforcement Learning for Extractive Legal Summarization

2021-11-13 · Duy-Hung Nguyen, Bao-Sinh Nguyen, Nguyen Viet Dung Nghiem, Dung Tien Le 외

Automatic summarization of legal texts is an important and still a challenging task since legal documents are often long and complicated with unusual structures and styles. Recent advances of deep models trained end-to-e…

Deep Reinforcement Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

TIAO: Token Importance-Aware Policy Optimization for Text Summarization

2026-09-15 · Qixiu Li, Chenlong Bao, Xiang Zhu, Xiaoyong Li 외 arxiv

Text summarization requires models to condense content while preserving key qualities such as consistency and coherence. Large language models (LLMs) have shown strong performance on this task and can be further improved…

Reinforcement Learning Text Summarization

ROSUM-MCTS: Monte Carlo Tree Search-Inspired HDL Code Summarization with Structural Rewards

2026-06-06 · Prashanth Vijayaraghavan, Charles Mackin, Luyao Shi, Apoorva Nitsure 외 arxiv

Large language models (LLMs) have shown promise in code summarization, yet their effectiveness for Hardware Description Languages (HDLs) like VHDL and Verilog remains underexplored. We propose ROSUM-MCTS, an LLM-guided a…