# Disentangling Specificity for Abstractive Multi-document Summarization

arXiv: https://arxiv.org/abs/2406.00005 · HTML: https://mlsanity.com/paper/2406.00005/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 28 references that are in the map.
- First posted on arXiv 12 May 2024.

## Builds on (most cited first, 19 of 19)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [Get To The Point: Summarization with Pointer-Generator Networks](https://mlsanity.com/paper/1704.04368/) (2017)
- [Multi-News: a Large-Scale Multi-Document Summarization Dataset and Abstractive Hierarchical Model](https://mlsanity.com/paper/1906.01749/) (2019)
- [Newsroom: A Dataset of 1.3 Million Summaries with Diverse Extractive Strategies](https://mlsanity.com/paper/1804.11283/) (2018)
- [Hierarchical Transformers for Multi-Document Summarization](https://mlsanity.com/paper/1905.13164/) (2019)
- [Multi-XScience: A Large-scale Dataset for Extreme Multi-document Summarization of Scientific Articles](https://mlsanity.com/paper/2010.14235/) (2020)
- [Heterogeneous Graph Neural Networks for Extractive Document Summarization](https://mlsanity.com/paper/2004.12393/) (2020)
- [Leveraging Graph to Improve Abstractive Multi-Document Summarization](https://mlsanity.com/paper/2005.10043/) (2020)
- [PRIMERA: Pyramid-based Masked Sentence Pre-training for Multi-document Summarization](https://mlsanity.com/paper/2110.08499/) (2021)
- [Multi-document Summarization via Deep Learning Techniques: A Survey](https://mlsanity.com/paper/2011.04843/) (2020)
- [Multi-document Summarization with Maximal Marginal Relevance-guided Reinforcement Learning](https://mlsanity.com/paper/2010.00117/) (2020)
- [SummPip: Unsupervised Multi-Document Summarization with Sentence Graph Compression](https://mlsanity.com/paper/2007.08954/) (2020)
- [Proposition-Level Clustering for Multi-Document Summarization](https://mlsanity.com/paper/2112.08770/) (2021)
- [Improving Multi-Document Summarization through Referenced Flexible Extraction with Credit-Awareness](https://mlsanity.com/paper/2205.01889/) (2022)
- [Read Top News First: A Document Reordering Approach for Multi-Document News Summarization](https://mlsanity.com/paper/2203.10254/) (2022)
- [How "Multi" is Multi-Document Summarization?](https://mlsanity.com/paper/2210.12688/) (2022)
- [Document-aware Positional Encoding and Linguistic-guided Encoding for Abstractive Multi-document Summarization](https://mlsanity.com/paper/2209.05929/) (2022)

## Built on by (most cited first, 1 of 1)

- [ResearchPulse: Building Method-Experiment Chains through Multi-Document Scientific Inference](https://mlsanity.com/paper/2509.03565/) (2025)

## Abstract (arXiv)

Multi-document summarization (MDS) generates a summary from a document set. Each document in a set describes topic-relevant concepts, while per document also has its unique contents. However, the document specificity receives little attention from existing MDS approaches. Neglecting specific information for each document limits the comprehensiveness of the generated summaries. To solve this problem, in this paper, we propose to disentangle the specific content from documents in one document set. The document-specific representations, which are encouraged to be distant from each other via a proposed orthogonal constraint, are learned by the specific representation learner. We provide extensive analysis and have interesting findings that specific information and document set representations contribute distinctive strengths and their combination yields a more comprehensive solution for the MDS. Also, we find that the common (i.e. shared) information could not contribute much to the overall performance under the MDS settings. Implemetation codes are available at https://github.com/congboma/DisentangleSum.