# Multi-document Summarization with Maximal Marginal Relevance-guided Reinforcement Learning

arXiv: https://arxiv.org/abs/2010.00117 · HTML: https://mlsanity.com/paper/2010.00117/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Sep 2020.

## Built on by (most cited first, 28 of 28)

- [PRIMERA: Pyramid-based Masked Sentence Pre-training for Multi-document Summarization](https://mlsanity.com/paper/2110.08499/) (2021)
- [Open Domain Multi-document Summarization: A Comprehensive Study of Model Brittleness under Retrieval](https://mlsanity.com/paper/2212.10526/) (2022)
- [CiteSum: Citation Text-guided Scientific Extreme Summarization and Domain Adaptation with Limited Supervision](https://mlsanity.com/paper/2205.06207/) (2022)
- [Proposition-Level Clustering for Multi-Document Summarization](https://mlsanity.com/paper/2112.08770/) (2021)
- [SummQA at MEDIQA-Chat 2023:In-Context Learning with GPT-4 for Medical Summarization](https://mlsanity.com/paper/2306.17384/) (2023)
- [AgreeSum: Agreement-Oriented Multi-Document Summarization](https://mlsanity.com/paper/2106.02278/) (2021)
- [MDCure: A Scalable Pipeline for Multi-Document Instruction-Following](https://mlsanity.com/paper/2410.23463/) (2024)
- [GlobeSumm: A Challenging Benchmark Towards Unifying Multi-lingual, Cross-lingual and Multi-document News Summarization](https://mlsanity.com/paper/2410.04087/) (2024)
- [How "Multi" is Multi-Document Summarization?](https://mlsanity.com/paper/2210.12688/) (2022)
- [PDSum: Prototype-driven Continuous Summarization of Evolving Multi-document Sets Stream](https://mlsanity.com/paper/2302.05550/) (2023)
- [The Power of Summary-Source Alignments](https://mlsanity.com/paper/2406.00842/) (2024)
- [Absformer: Transformer-based Model for Unsupervised Multi-Document Abstractive Summarization](https://mlsanity.com/paper/2306.04787/) (2023)
- [DynED: Dynamic Ensemble Diversification in Data Stream Classification](https://mlsanity.com/paper/2308.10807/) (2023)
- [Extract, Denoise and Enforce: Evaluating and Improving Concept Preservation for Text-to-Text Generation](https://mlsanity.com/paper/2104.08724/) (2021)
- [Modeling Endorsement for Multi-Document Abstractive Summarization](https://mlsanity.com/paper/2110.07844/) (2021)
- [Combining State-of-the-Art Models with Maximal Marginal Relevance for Few-Shot and Zero-Shot Multi-Document Summarization](https://mlsanity.com/paper/2211.10808/) (2022)
- [Discourse-Aware In-Context Learning for Temporal Expression Normalization](https://mlsanity.com/paper/2404.07775/) (2024)
- [Multi-document Summarization through Multi-document Event Relation Graph Reasoning in LLMs: a case study in Framing Bias Mitigation](https://mlsanity.com/paper/2506.12978/) (2025)
- [A Multi-Document Coverage Reward for RELAXed Multi-Document Summarization](https://mlsanity.com/paper/2203.02894/) (2022)
- [Dont Add, dont Miss: Effective Content Preserving Generation from Pre-Selected Text Spans](https://mlsanity.com/paper/2310.09017/) (2023)
- [Disentangling Specificity for Abstractive Multi-document Summarization](https://mlsanity.com/paper/2406.00005/) (2024)
- [GLIMMER: Incorporating Graph and Lexical Features in Unsupervised Multi-Document Summarization](https://mlsanity.com/paper/2408.10115/) (2024)
- [Evaluating the Performance of RAG Methods for Conversational AI in the Airport Domain](https://mlsanity.com/paper/2505.13006/) (2025)
- [A Unifying Scheme for Extractive Content Selection Tasks](https://mlsanity.com/paper/2507.16922/) (2025)
- [Multi-Document Keyphrase Extraction: Dataset, Baselines and Review](https://mlsanity.com/paper/2110.01073/) (2021)
- [Rethinking Transformer-based Multi-document Summarization: An Empirical Investigation](https://mlsanity.com/paper/2407.11948/) (2024)
- [A Unified Retrieval Framework with Document Ranking and EDU Filtering for Multi-document Summarization](https://mlsanity.com/paper/2504.16711/) (2025)
- [OPOR-Bench: Evaluating Large Language Models on Online Public Opinion Report Generation](https://mlsanity.com/paper/2512.01896/) (2025)

## Abstract (arXiv)

While neural sequence learning methods have made significant progress in single-document summarization (SDS), they produce unsatisfactory results on multi-document summarization (MDS). We observe two major challenges when adapting SDS advances to MDS: (1) MDS involves larger search space and yet more limited training data, setting obstacles for neural methods to learn adequate representations; (2) MDS needs to resolve higher information redundancy among the source documents, which SDS methods are less effective to handle. To close the gap, we present RL-MMR, Maximal Margin Relevance-guided Reinforcement Learning for MDS, which unifies advanced neural SDS methods and statistical measures used in classical MDS. RL-MMR casts MMR guidance on fewer promising candidates, which restrains the search space and thus leads to better representation learning. Additionally, the explicit redundancy measure in MMR helps the neural representation of the summary to better capture redundancy. Extensive experiments demonstrate that RL-MMR achieves state-of-the-art performance on benchmark MDS datasets. In particular, we show the benefits of incorporating MMR into end-to-end learning when adapting SDS to MDS in terms of both learning effectiveness and efficiency.