Topic-Guided Reinforcement Learning with LLMs for Enhancing Multi-Document Summarization

Chuyuan Li, Austin Xu, Shafiq Joty, Giuseppe Carenini


Abstract
A key challenge in Multi-Document Summarization (MDS) is effectively integrating information from multiple sources while maintaining coherence and topical relevance. While Large Language Models (LLMs) have shown impressive results in single-document summarization, their performance on MDS still leaves room for improvement. In this paper, we propose a topic-guided reinforcement learning approach to improve content selection in MDS. We first show that explicitly prompting models with topic labels enhances the informativeness. Building on this insight, we propose a novel topic reward within the Group Relative Policy Optimization (GRPO) framework to measure topic alignment between the generated summary and source documents. Experimental results on the Multi-News and Multi-XScience datasets demonstrate that our method consistently outperforms strong baselines, highlighting the effectiveness of leveraging topical cues in MDS.
Anthology ID:
2025.findings-emnlp.662
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2025
Month:
November
Year:
2025
Address:
Suzhou, China
Editors:
Christos Christodoulopoulos, Tanmoy Chakraborty, Carolyn Rose, Violet Peng
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
12395–12412
Language:
URL:
https://aclanthology.org/2025.findings-emnlp.662/
DOI:
Bibkey:
Cite (ACL):
Chuyuan Li, Austin Xu, Shafiq Joty, and Giuseppe Carenini. 2025. Topic-Guided Reinforcement Learning with LLMs for Enhancing Multi-Document Summarization. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 12395–12412, Suzhou, China. Association for Computational Linguistics.
Cite (Informal):
Topic-Guided Reinforcement Learning with LLMs for Enhancing Multi-Document Summarization (Li et al., Findings 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.findings-emnlp.662.pdf
Checklist:
 2025.findings-emnlp.662.checklist.pdf