EMNLP Findings2025
Topic-Guided Reinforcement Learning with LLMs for Enhancing Multi-Document Summarization
摘要
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 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 of the generated summaries. 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. 1
问 Lune
几分钟读透这篇 Paper,不用再花一下午。
Lune 能读完全文,也能读引用它的顶会 Paper,讲清它的结论、证据和局限,每一点都注明出自哪篇 Paper。不用硬啃,也不靠猜。
脉络
它引用的 Paper15
- BERTScore: Evaluating Text Generation with BERTTianyi Zhang, Varsha Kishore, Felix Wu, Kilian Q. Weinberger 等ICLR 2020 · 8,443 次引用
- SimCSE: Simple Contrastive Learning of Sentence EmbeddingsTianyu Gao, Xingcheng Yao, Danqi ChenEMNLP 2021 · 2,496 次引用
- PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive SummarizationJingqing Zhang, Yao Zhao, Mohammad Saleh, Peter J. LiuICML 2020 · 2,453 次引用
- Can Large Language Models Be an Alternative to Human Evaluations?David Cheng-Han Chiang, Hung-yi LeeACL 2023 · 254 次引用
- PRIMERA: Pyramid-based Masked Sentence Pre-training for Multi-document SummarizationWen Xiao, Iz Beltagy, Giuseppe Carenini, Arman CohanACL 2022 · 147 次引用
相关 Paper
- Multi-document Summarization with Maximal Marginal Relevance-guided Reinforcement LearningYuning Mao, Yanru Qu, Yiqing Xie, Xiang Ren 等EMNLP 2020 · 43 次引用
- A Multi-Document Coverage Reward for RELAXed Multi-Document SummarizationJacob Parnell, Inigo Jauregi Unanue, Massimo PiccardiACL 2022 · 16 次引用
- Topic-Guided Abstractive Multi-Document SummarizationPeng Cui, Le HuEMNLP Findings 2021 · 38 次引用
- Boosting Multi-Domain Reasoning of LLMs via Curvature-Guided Policy OptimizationXize Liang, Lin Yang, Jie Wang, Rui Liu 等ICLR 2026
- A Hierarchical Encoding-Decoding Scheme for Abstractive Multi-document SummarizationChenhui Shen, Liying Cheng, Xuan-Phi Nguyen, Yang You 等EMNLP Findings 2023 · 18 次引用
