Topic-Guided Reinforcement Learning with LLMs for Enhancing Multi-Document Summarization
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912584564736000 |
|---|---|
| author | Li, Chuyuan Xu, Austin Joty, Shafiq Carenini, Giuseppe |
| author_facet | Li, Chuyuan Xu, Austin Joty, Shafiq Carenini, Giuseppe |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_09852 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Topic-Guided Reinforcement Learning with LLMs for Enhancing Multi-Document Summarization Li, Chuyuan Xu, Austin Joty, Shafiq Carenini, Giuseppe Computation and Language 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. |
| title | Topic-Guided Reinforcement Learning with LLMs for Enhancing Multi-Document Summarization |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2509.09852 |