# DynE: Dynamic Ensemble Decoding for Multi-Document Summarization

arXiv: https://arxiv.org/abs/2006.08748 · HTML: https://mlsanity.com/paper/2006.08748/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Jun 2020.

## Built on by (most cited first, 8 of 8)

- [Speculative Decoding with Big Little Decoder](https://mlsanity.com/paper/2302.07863/) (2023)
- [PRIMERA: Pyramid-based Masked Sentence Pre-training for Multi-document Summarization](https://mlsanity.com/paper/2110.08499/) (2021)
- [Cost-Effective Online Multi-LLM Selection with Versatile Reward Models](https://mlsanity.com/paper/2405.16587/) (2024)
- [Chunk, Align, Select: A Simple Long-sequence Processing Method for Transformers](https://mlsanity.com/paper/2308.13191/) (2023)
- [A Hierarchical Encoding-Decoding Scheme for Abstractive Multi-document Summarization](https://mlsanity.com/paper/2305.08503/) (2023)
- [A Multi-Document Coverage Reward for RELAXed Multi-Document Summarization](https://mlsanity.com/paper/2203.02894/) (2022)
- [Controllable Multi-document Summarization: Coverage & Coherence Intuitive Policy with Large Language Model Based Rewards](https://mlsanity.com/paper/2310.03473/) (2023)
- [Mining both Commonality and Specificity from Multiple Documents for Multi-Document Summarization](https://mlsanity.com/paper/2303.02677/) (2023)

## Abstract (arXiv)

Sequence-to-sequence (s2s) models are the basis for extensive work in natural language processing. However, some applications, such as multi-document summarization, multi-modal machine translation, and the automatic post-editing of machine translation, require mapping a set of multiple distinct inputs into a single output sequence. Recent work has introduced bespoke architectures for these multi-input settings, and developed models which can handle increasingly longer inputs; however, the performance of special model architectures is limited by the available in-domain training data. In this work we propose a simple decoding methodology which ensembles the output of multiple instances of the same model on different inputs. Our proposed approach allows models trained for vanilla s2s tasks to be directly used in multi-input settings. This works particularly well when each of the inputs has significant overlap with the others, as when compressing a cluster of news articles about the same event into a single coherent summary, and we obtain state-of-the-art results on several multi-document summarization datasets.