mlsanityData to 14 Oct 2026

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

arXiv 2509.09852 ↗First posted 11 Sep 2025cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 46 of its 64 references that are in the map. First posted on arXiv 11 Sep 2025.

Builds on

46 of 64 references.

References · 46

  1. 2022Training language models to follow instructions with human feedbackcited by 15,971
  2. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  3. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,626
  4. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,512
  5. 2020Learning to summarize from human feedbackcited by 2,588
  6. 2021SimCSE: Simple Contrastive Learning of Sentence Embeddingscited by 2,173
  7. 2019Fine-Tuning Language Models from Human Preferencescited by 2,150
  8. 2017Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semanticscited by 1,358
  9. 2018Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarizationcited by 1,317
  10. 2019PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarizationcited by 1,102
  11. 2023Can Large Language Models Be an Alternative to Human Evaluations?cited by 734
  12. 2020SummEval: Re-evaluating Summarization Evaluationcited by 674
34 more
  1. 2015Sequence Level Training with Recurrent Neural Networkscited by 576
  2. 2018A Discourse-Aware Attention Model for Abstractive Summarization of Long Documentscited by 478
  3. 2019Multi-News: a Large-Scale Multi-Document Summarization Dataset and Abstractive Hierarchical Modelcited by 431
  4. 2021SummaC: Re-Visiting NLI-based Models for Inconsistency Detection in Summarizationcited by 407
  5. 2024LLM2Vec: Large Language Models Are Secretly Powerful Text Encoderscited by 404
  6. 2017A Deep Reinforced Model for Abstractive Summarizationcited by 365
  7. 2021QMSum: A New Benchmark for Query-based Multi-domain Meeting Summarizationcited by 365
  8. 2022News Summarization and Evaluation in the Era of GPT-3cited by 327
  9. 2014A Survey of Multi-Objective Sequential Decision-Makingcited by 242
  10. 2019Neural Text Summarization: A Critical Evaluationcited by 189
  11. 2020GSum: A General Framework for Guided Neural Abstractive Summarizationcited by 129
  12. 2020Pre-training is a Hot Topic: Contextualized Document Embeddings Improve Topic Coherencecited by 121
  13. 2020Multi-XScience: A Large-scale Dataset for Extreme Multi-document Summarization of Scientific Articlescited by 97
  14. 2024Summary of a Haystack: A Challenge to Long-Context LLMs and RAG Systemscited by 87
  15. 2021Planning with Learned Entity Prompts for Abstractive Summarizationcited by 75
  16. 2018Multi-Reward Reinforced Summarization with Saliency and Entailmentcited by 73
  17. 2023LLM Comparative Assessment: Zero-shot NLG Evaluation through Pairwise Comparisons using Large Language Modelscited by 71
  18. 2015Simple, Robust and Optimal Ranking from Pairwise Comparisonscited by 70
  19. 2023Benchmarking Generation and Evaluation Capabilities of Large Language Models for Instruction Controllable Summarizationcited by 69
  20. 2018Learning to Extract Coherent Summary via Deep Reinforcement Learningcited by 64
  21. 2017Hybrid Reward Architecture for Reinforcement Learningcited by 58
  22. 2020Multi-document Summarization via Deep Learning Techniques: A Surveycited by 58
  23. 2022Conditional Generation with a Question-Answering Blueprintcited by 44
  24. 2020Enhancing Extractive Text Summarization with Topic-Aware Graph Neural Networkscited by 22
  25. 2018A Reinforced Topic-Aware Convolutional Sequence-to-Sequence Model for Abstractive Text Summarizationcited by 21
  26. 2021Topic-Guided Abstractive Multi-Document Summarizationcited by 19
  27. 2023OpenAsp: A Benchmark for Multi-document Open Aspect-based Summarizationcited by 15
  28. 2025Multi2: Multi-Agent Test-Time Scalable Framework for Multi-Document Processingcited by 12
  29. 2022Multi-Document Scientific Summarization from a Knowledge Graph-Centric Viewcited by 11
  30. 2022Read Top News First: A Document Reordering Approach for Multi-Document News Summarizationcited by 9
  31. 2024PositionID: LLMs can Control Lengths, Copy and Paste with Explicit Positional Awarenesscited by 9
  32. 2025J4R: Learning to Judge with Equivalent Initial State Group Relative Policy Optimizationcited by 9
  33. 2024SEAM: A Stochastic Benchmark for Multi-Document Taskscited by 8
  34. 2023CWTM: Leveraging Contextualized Word Embeddings from BERT for Neural Topic Modelingcited by 7

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Multi-Dimensional Optimization for Text Summarization via Reinforcement Learning
  2. 2025Balancing Rewards in Text Summarization: Multi-Objective Reinforcement Learning via HyperVolume Optimization
  3. 2022Towards Abstractive Timeline Summarisation using Preference-based Reinforcement Learning
  4. 2026TIAO: Token Importance-Aware Policy Optimization for Text Summarization
  5. 2025MM-R5: MultiModal Reasoning-Enhanced ReRanker via Reinforcement Learning for Document Retrieval
  6. 2025Advancing Speech Summarization in Multi-modal LLMs with Reinforcement Learning
  7. 2025DocR1: Evidence Page-Guided GRPO for Multi-Page Document Understanding
  8. 2026A Training-Free Mixture-of-Agents Framework for Multi-Document Summarization using LLMs and Knowledge Graphs