MULTI-DOCUMENT SUMMARIZATION

Discriminative Marginalized Probabilistic Neural Method for Multi-Document Summarization of Medical Literature (2022.acl-long)

Challenge:	Existing methods for summarizing documents rely on hand-crafted features or additional annotated data.
Approach:	They propose a method that makes use of two types of sentence embeddings . the method uses universal embeddable and domain-specific embeddible features .
Outcome:	The proposed method achieves competitive results on two types of summary, consisting of 665 bytes and 100 words.

Copied to clipboard

Gianluca Moro, Luca Ragazzi, Lorenzo Valgimigli, Davide Freddi

Tractable & Coherent Multi-Document Summarization: Discrete Optimization of Multiple Neural Modeling Streams via Integer Linear Programming (2022.emnlp-industry)

Challenge:	Existing solutions for multi-document summarization ignore potential summary-relevant contents, causing problems in the medical domain.
Approach:	They propose a discriminative marginalized probabilistic method to generate a multi-document summary from a cluster of topic-related medical documents using token probability marginalization.
Outcome:	The proposed method outperforms the current state-of-the-art on a biomedical dataset for multi-document summarization.

Copied to clipboard

Litton J Kurisinkel, Nancy Chen

SummerTime: Text Summarization Toolkit for Non-experts (2021.emnlp-demo)

Challenge:	Multi-document summarization generates summary of corpus of documents consisting of related topics.
Approach:	They propose a generic framework to jointly consider coherence and informativeness in multi-document summarization and offers provisions to replace individual components based on the domain of source text.
Outcome:	The proposed framework consistently performs better than baselines for objective metrics and human evaluation.

Copied to clipboard

Ansong Ni, Zhangir Azerbayev, Mutethia Mutuma, Troy Feng, Yusen Zhang, Tao Yu, Ahmed Hassan Awadallah, Dragomir Radev

Improving Factuality in Clinical Abstractive Multi-Document Summarization by Guided Continued Pre-training (2024.naacl-short)

Challenge:	Recent advances in summarization provide models that can generate high quality summaries . a new toolkit for summarizing text is being developed to make it easier for non-experts to keep track of them.
Approach:	They develop a toolkit for text summarization that integrates with libraries designed for NLP researchers.
Outcome:	SummerTime is a toolkit for text summarization, including models, datasets, and evaluation metrics.

Copied to clipboard

Ahmed Elhady, Khaled Elsayed, Eneko Agirre, Mikel Artetxe

Improving Fairness of Large Language Models in Multi-document Summarization (2025.acl-short)

Challenge:	Existing methods for enhancing the factual accuracy of abstractive summarization models are not effective in fact-critical domains like clinical document summarizing.
Approach:	They propose a guided continued pre-training stage for encoder-decoder models followed by supervised fine-tuning on summarization.
Outcome:	The proposed approach improves the quality and factuality of the summaries and achieves the best-published results on the clinical document summarization task.

Copied to clipboard

Haoyuan Li, Rui Zhang, Snigdha Chaturvedi

Ethical NLP

Challenge:	Recent studies focus on summary-level fairness, while corpus-level focuses on corpus of summaries.
Approach:	They propose a preference tuning method that focuses on both summary-level and corpus-level fairness in MDS.
Outcome:	The proposed method outperforms baselines while maintaining critical qualities of summaries.

Improving the Similarity Measure of Determinantal Point Processes for Extractive Multi-Document Summarization (P19-1)

Copied to clipboard

Sangwoo Cho, Logan Lebanoff, Hassan Foroosh, Fei Liu

Abstract Meaning Representation for Multi-Document Summarization (C18-1)

Challenge:	Despite the empirical success of multi-document summarization, most datasets remain small and the cost of hiring hu-1 is prohibitive.
Approach:	They propose a novel method for extractive multi-document summarization that measures redundancy between a pair of sentences based on surface form and semantic information.
Outcome:	The proposed method outperforms baseline methods on benchmark datasets and is particularly useful for documents created by multiple authors containing redundant yet lexically diverse expressions.

Copied to clipboard

Kexin Liao, Logan Lebanoff, Fei Liu

Semantic Text Processing

Challenge:	Abstract Meaning Representation (AMR) is a semantic representation of natural language based on linguistic theory .
Approach:	They propose to use Abstract Meaning Representation (AMR) as a content representation.
Outcome:	The proposed framework is fully data-driven and flexible.

Multi-News: A Large-Scale Multi-Document Summarization Dataset and Abstractive Hierarchical Model (P19-1)

Copied to clipboard

Alexander Fabbri, Irene Li, Tianwei She, Suyi Li, Dragomir Radev

Topic-Guided Abstractive Multi-Document Summarization (2021.findings-emnlp)

Challenge:	Multi-document summarization (MDS) of news articles has been limited to datasets of a couple of hundred examples.
Approach:	They propose a model which integrates a traditional extractive summarization model with a standard SDS model and achieves competitive results on MDS datasets.
Outcome:	The proposed model achieves competitive results on large-scale datasets.

Copied to clipboard

Peng Cui, Le Hu

Proposition-Level Clustering for Multi-Document Summarization (2022.naacl-main)

Challenge:	Existing studies on multi-document summarization (MDS) focus on extractive and abstractive approaches to create a fluent and concise summary for a collection of thematically related documents.
Approach:	They propose a novel abstractive MDS model that represents multiple documents as a heterogeneous graph and then applies a graph-to-sequence framework to generate summaries.
Outcome:	The proposed model outperforms state-of-the-art models on Rouge scores and human evaluation, while learning high-quality topics.

Copied to clipboard

Ori Ernst, Avi Caciularu, Ori Shapira, Ramakanth Pasunuru, Mohit Bansal, Jacob Goldberger, Ido Dagan

MiRANews: Dataset and Benchmarks for Multi-Resource-Assisted News Summarization (2021.findings-emnlp)

Challenge:	Existing methods focused on clustering sentences to indicate information saliency and avoid redundancy.
Approach:	They propose to group together sub-sentential propositions to generate a representative sentence for each cluster via text fusion.
Outcome:	The proposed method improves over the previous state-of-the-art method in the DUC 2004 and TAC 2011 datasets, both in automatic ROUGE scores and human preference.

Copied to clipboard

Xinnuo Xu, Ondřej Dušek, Shashi Narayan, Verena Rieser, Ioannis Konstas

Summarization

Challenge:	Current news summarization systems often contain 'extrinsic hallucinations', i.e. facts that are not present in the source document, which are often derived via world knowledge.
Approach:	They propose to use multiple supplementary resource documents to assist the task by pairing a single document with a human authored summary as the summary.
Outcome:	The proposed model reduces 55% of hallucinations when compared to single-document summarization models trained on the main article only.

Multi-document Summarization with Maximal Marginal Relevance-guided Reinforcement Learning (2020.emnlp-main)

Copied to clipboard

Yuning Mao, Yanru Qu, Yiqing Xie, Xiang Ren, Jiawei Han

Abstractive Multi-Document Summarization via Joint Learning with Single-Document Summarization (2020.findings-emnlp)

Challenge:	Recent studies on single-document summarization (SDS) benefit from advances in neural sequence learning, but they produce unsatisfactory results on multi-document summary (MDS).
Approach:	They propose a neural sequence learning method that unifies advanced neural SDS methods and statistical measures used in classical MDS.
Outcome:	The proposed method achieves state-of-the-art performance on benchmark MDS datasets.

Copied to clipboard

Hanqi Jin, Xiaojun Wan

Leveraging Digitized Newspapers to Collect Summarization Data in Low-Resource Languages (2026.findings-eacl)

Challenge:	Existing methods for document summarization are extractive and abstractive.
Approach:	They propose to jointly learn an abstractive single-document decoder and a decoding controller to aggregate the decoded outputs for multiple input documents.
Outcome:	The proposed model outperforms several baselines on two multi-document summarization datasets and proves that it is useful for both tasks.

Copied to clipboard

Noam Dahan, Omer Kidron, Gabriel Stanovsky

From Single to Multi: How LLMs Hallucinate in Multi-Document Summarization (2025.findings-naacl)

Challenge:	Recent studies suggest that summarization in English may be solved, or even "dead" However, there are no accessible, high-quality summarizing datasets in under-represented languages.
Approach:	They propose a method for collecting naturally occurring summaries via front-page teasers, where editors summarize full length articles.
Outcome:	The proposed method is suited to varying linguistic resources and is available in seven languages.

Copied to clipboard

Catarina G Belém, Pouya Pezeshkpour, Hayate Iso, Seiji Maekawa, Nikita Bhutani, Estevam Hruschka

Subtopic-driven Multi-Document Summarization (D19-1)

Challenge:	a recent study investigated hallucinations in multi-document summarization tasks . but, it is unclear how challenges arising from handling multiple documents affect outputs .
Approach:	They investigate how hallucinations manifest in large language models when summarizing topic-specific information from a set of documents.
Outcome:	The proposed benchmarks show that the models generate more hallucinations than baselines . the results highlight the need for more effective approaches to mitigate hallucinosity in MDS .

Copied to clipboard

Xin Zheng, Aixin Sun, Jing Li, Karthik Muthuswamy

Which Information Matters? Dissecting Human-written Multi-document Summaries with Partial Information Decomposition (2024.findings-acl)

Challenge:	Experimental results show that the proposed model outperforms state-of-the-art methods on benchmark datasets.
Approach:	They propose a multi-document summarization model that assumes a set of documents to be summarized is on the same topic.
Outcome:	The proposed model outperforms state-of-the-art methods on benchmark datasets.

Copied to clipboard

Laura Mascarell, Yan LHomme, Majed El Helou

Summarization

Challenge:	Existing methods to characterize human-written summaries do not account for the nature of high-quality summary.
Approach:	They propose to characterize human-written summaries using partial information decomposition . they propose to decompose mutual information provided by all source documents into union, redundancy, synergy, and unique information .
Outcome:	The proposed approach decomposes the mutual information provided by all source documents into union, redundancy, synergy, and unique information.

PRIMERA: Pyramid-based Masked Sentence Pre-training for Multi-document Summarization (2022.acl-long)

Copied to clipboard

Wen Xiao, Iz Beltagy, Giuseppe Carenini, Arman Cohan

SupMMD: A Sentence Importance Model for Extractive Summarization using Maximum Mean Discrepancy (2020.findings-emnlp)

Challenge:	Existing pretrained models require domain-specific additional information to be effective.
Approach:	They propose a pre-trained model for multi-document representation with a focus on summarization that uses efficient encoder-decoder transformers to simplify the processing of concatenated input documents.
Outcome:	PRIMERA outperforms current state-of-the-art models on most datasets with large margins . PRImerA uses efficient encoder-decoder transformers to simplify processing of concatenated input documents.

Copied to clipboard

Umanga Bista, Alexander Mathews, Aditya Menon, Lexing Xie

Efficiently Summarizing Text and Graph Encodings of Multi-Document Clusters (2021.naacl-main)

Challenge:	Existing work on multi-document summarization has focused on generic summarizing of information present in each document set.
Approach:	They propose a technique for generic and update summarization based on kernel two-sample testing.
Outcome:	The proposed technique exceeds the current state-of-the-art on two datasets.

Copied to clipboard

Ramakanth Pasunuru, Mengwen Liu, Mohit Bansal, Sujith Ravi, Markus Dreyer

How “Multi” is Multi-Document Summarization? (2022.emnlp-main)

Challenge:	Abstractive multi-document summarization (MDS) is a task that has seen advances with the introduction of large-scale datasets and powerful Transformer-based models.
Approach:	They propose an efficient graph-enhanced approach to multi-document summarization with an encoder-decoder Transformer model.
Outcome:	The proposed model scales to large input documents and improves on a multi-document dataset.

Copied to clipboard

Ruben Wolhandler, Arie Cattan, Ori Ernst, Ido Dagan

A Hierarchical Encoding-Decoding Scheme for Abstractive Multi-document Summarization (2023.findings-emnlp)

Challenge:	Multi-document summarization (MDS) aims at combining information spread across multiple documents . a single document often covers the full summary content .
Approach:	They propose a measure to evaluate the degree to which a summary is "disperse" they propose to combine information from multiple documents into a single document to generate a concise summary .
Outcome:	The proposed measure evaluates the degree to which a summary is "disperse" the measure is applied to several popular MDS datasets and state-of-the-art systems.

Copied to clipboard

Chenhui Shen, Liying Cheng, Xuan-Phi Nguyen, Yang You, Lidong Bing

Using Local Knowledge Graph Construction to Scale Seq2Seq Models to Multi-Document Inputs (D19-1)

Challenge:	Pre-trained language models have been used for abstractive single-document summarization (SDS) but they may not be suitable for multi-document summary (MDS)
Approach:	They propose to enforce hierarchy on both encoder and decoder to facilitate multi-document interactions for MDS.
Outcome:	Xiao et al. (2019) outperforms or is competitive with the previous best models.

Copied to clipboard

Angela Fan, Claire Gardent, Chloé Braud, Antoine Bordes

Semantic Text Processing

Challenge:	Current approaches extract portions of web text as input to Sequence-to-Sequence models . a problem is generating relevant knowledge from noisy and redundant input such as webpages .
Approach:	They propose to restructure free text into local knowledge graphs that are linearized into sequences . they propose to encode the graph as a sequence and then linearize it into a structured sequence .
Outcome:	The proposed method compresses web search information and reduces redundancy . it can be used for open-domain question answering and multi-document summarization tasks .

Revisiting Sentence Union Generation as a Testbed for Text Consolidation (2023.findings-acl)

Copied to clipboard

Eran Hirsch, Valentina Pyatkin, Ruben Wolhandler, Avi Caciularu, Asi Shefer, Ido Dagan

Challenge:	In order to acquire knowledge on a new subject, it is often necessary to consult multiple sources of written information.
Approach:	They propose to revisit the sentence union generation task as an effective well-defined testbed for assessing text consolidation capabilities.
Outcome:	The proposed evaluation protocol includes human and automatic evaluations.

Adapting the Neural Encoder-Decoder Framework from Single to Multi-Document Summarization (D18-1)

Copied to clipboard

Logan Lebanoff, Kaiqiang Song, Fei Liu

Transfer Learning for Sequence Generation: from Single-source to Multi-source (2021.acl-long)

Challenge:	Existing methods to summarize short texts using a neural encoder-decoder are limited and expensive to obtain.
Approach:	They propose to use a maximal marginal relevance method to select representative sentences from multi-document input and leverage an abstractive encoder-decoder model to fuse disparate sentences to an abstract.
Outcome:	The proposed method compares favorably to state-of-the-art extractive and abstractive approaches judged by automatic metrics and human assessors.

Copied to clipboard

Xuancheng Huang, Jingfang Xu, Maosong Sun, Yang Liu

Coverage-based Fairness in Multi-document Summarization (2025.naacl-long)

Challenge:	Recent studies have shown that pretrained models are effective for low-resource downstream tasks.
Approach:	They propose a two-stage finetuning method to transfer pretrained models to MSG tasks by concatenating multiple sources into a single long sequence.
Outcome:	The proposed model outperforms baselines on the WMT17 APE task and multi-source translation task using the WTM14 test set.

Copied to clipboard

Haoyuan Li, Yusen Zhang, Rui Zhang, Snigdha Chaturvedi

Responsible & Trustworthy NLP

Challenge:	Existing studies quantify summary-level fairness using Proportional Representation, but they ignore corpus-level unfairness.
Approach:	They propose a new summary-level fairness measure that considers redundancy in documents . they evaluate the fairness of thirteen different multi-document summarization systems .
Outcome:	The proposed measure is based on coverage of documents with different social attribute values and considers redundancy within documents.

Auto-hMDS: Automatic Construction of a Large Heterogeneous Multilingual Multi-Document Summarization Corpus (L18-1)

Copied to clipboard

Markus Zopf

MSˆ2: Multi-Document Summarization of Medical Studies (2021.emnlp-main)

Challenge:	Existing datasets for automatic text summarization are small and focused on newswires.
Approach:	They propose to automatically generate a large multilingual multi-document summarization corpus using Wikipedia articles as summaries and to automatically search for appropriate source documents.
Outcome:	The proposed corpus contains 7,316 topics in English and German with different summary lengths and number of source documents.

Copied to clipboard

Jay DeYoung, Iz Beltagy, Madeleine van Zuylen, Bailey Kuehl, Lucy Lu Wang

QA-Align: Representing Cross-Text Content Overlap by Aligning Question-Answer Propositions (2021.emnlp-main)

Challenge:	Existing datasets for multi-document summarization (MDS) are either in the general domain, such as WikiSum, or very small such as DUC 1 or TAC 2011 . Existing systems for summarizing biomedical literature take 1-2 years to complete .
Approach:	They propose to use a multi-document summarization system based on BART to assess the quality of the summarized biomedical literature.
Outcome:	The proposed system has high summarization quality, but significant work remains to achieve it.

Copied to clipboard

Daniela Brook Weiss, Paul Roit, Ayal Klein, Ori Ernst, Ido Dagan

Question Answering

Challenge:	Existing approaches to consolidate textual inputs are difficult to implement . a recent study aims to capture content overlap by combining multiple textual elements .
Approach:	They propose to align predicate-argument relations across texts to represent content overlap . their setting exploits QA-SRL, utilizing question-answer pairs to capture predicates .
Outcome:	The proposed task captures content overlap beyond lexical similarity and complements cross-document coreference with proposition-level links, offering potential use for downstream tasks.

GameWikiSum: a Novel Large Multi-Document Summarization Dataset (2020.lrec-1)

Copied to clipboard

Diego Antognini, Boi Faltings

LLM Agents for Coordinating Multi-User Information Gathering (2025.findings-acl)

Challenge:	Existing datasets contain only hundreds of samples, resulting in heavy reliance on hand-crafted features or manually annotated data.
Approach:	They propose a new domain-specific dataset for multi-document summarization that is 100 times larger than commonly used datasets.
Outcome:	The proposed dataset is 100 times larger than commonly used datasets and in another domain than news.

Copied to clipboard

Harsh Jhamtani, Jacob Andreas, Benjamin Van Durme

Principled Content Selection to Generate Diverse and Personalized Multi-Document Summaries (2025.acl-long)

Challenge:	Recent large language models (LLMs) are becoming a crucial building block in developing automated agents that can assist human users with complex tasks.
Approach:	They introduce PeopleJoin, a benchmark for evaluating LM-mediated collaborative problem solving.
Outcome:	The proposed benchmarks are adapted from existing benchmarks for database question answering and multi-document summarization.

Copied to clipboard

Vishakh Padmakumar, Zichao Wang, David Arbour, Jennifer Healey