| Long Document Summarization with Top-down and Bottom-up Inference | ✓ Link | 51.05 | 23.26 | 46.47 | Top Down Transformer (AdaPool) (464M) | 2022-03-15 |
| Scaling Up Summarization: Leveraging Large Language Models for Long Text Extractive Summarization | | 50.34 | 24.57 | 45.96 | eyeglaxs | 2024-08-28 |
| Adapting Pretrained Text-to-Text Models for Long Text Sequences | ✓ Link | 50.3 | | | BART-LS | 2022-09-21 |
| LongT5: Efficient Text-To-Text Transformer for Long Sequences | ✓ Link | 50.23 | 24.76 | 46.67 | LongT5 | 2021-12-15 |
| GoSum: Extractive Summarization of Long Documents by Reinforcement Learning and Graph Organized discourse state | ✓ Link | 49.83 | 23.56 | 45.10 | GoSum (extractive) | 2022-11-18 |
| Toward Unifying Text Segmentation and Long Document Summarization | ✓ Link | 49.38 | 23.89 | 44.84 | Lodoss-full-large (extractive) | 2022-10-28 |
| MemSum: Extractive Summarization of Long Documents Using Multi-Step Episodic Markov Decision Processes | ✓ Link | 49.25 | 22.94 | 44.42 | MemSum (extractive) | 2021-07-19 |
| Toward Unifying Text Segmentation and Long Document Summarization | ✓ Link | 48.93 | 23.51 | 44.40 | Lodoss-full-base (extractive) | 2022-10-28 |
| Hierarchical Learning for Generation with Long Source Sequences | | 48.25 | 21.35 | 36.69 | HAT-BART | 2021-04-15 |
| GRETEL: Graph Contrastive Topic Enhanced Language Model for Long Document Extractive Summarization | | 48.20 | 21.20 | 43.16 | GRETEL | 2022-08-21 |
| Sparsifying Transformer Models with Trainable Representation Pooling | ✓ Link | 47.81 | 21.14 | | DeepPyramidion | 2020-09-10 |
| Factorizing Content and Budget Decisions in Abstractive Summarization of Long Documents | ✓ Link | 47.5 | 20.33 | 43.76 | FactorSum | 2022-05-25 |
| HiStruct+: Improving Extractive Text Summarization with Hierarchical Structure Information | | 46.59 | 20.39 | 42.11 | HiStruct+ | 2022-03-17 |
| A Divide-and-Conquer Approach to the Summarization of Long Documents | ✓ Link | 46.34 | 19.97 | 42.42 | DANCER PEGASUS | 2020-04-13 |
| Big Bird: Transformers for Longer Sequences | ✓ Link | 46.32 | 20.65 | 42.33 | BigBird-Pegasus | 2020-07-28 |
| Systematically Exploring Redundancy Reduction in Summarizing Long Documents | ✓ Link | 45.39 | 20.37 | 40.99 | ExtSum-LG+MMR-Select+ | 2020-11-30 |
| Systematically Exploring Redundancy Reduction in Summarizing Long Documents | ✓ Link | 45.3 | 20.42 | 40.95 | ExtSum-LG+RdLoss | 2020-11-30 |
| PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization | ✓ Link | 45.09 | | | PEGASUS | 2019-12-18 |
| On Extractive and Abstractive Neural Document Summarization with Transformer Language Models | ✓ Link | 45.01 | | | Sent-CLF | 2019-09-07 |
| Extractive Summarization of Long Documents by Combining Global and Local Context | ✓ Link | 44.81 | 19.74 | | ExtSum-LG | 2019-09-17 |
| A Divide-and-Conquer Approach to the Summarization of Long Documents | ✓ Link | 44.09 | 17.69 | 40.27 | DANCER LSTM | 2020-04-13 |
| A Divide-and-Conquer Approach to the Summarization of Long Documents | ✓ Link | 43.98 | 17.65 | 40.25 | DANCER RUM | 2020-04-13 |
| On Extractive and Abstractive Neural Document Summarization with Transformer Language Models | ✓ Link | 43.3 | | | Sent-PTR | 2019-09-07 |
| GenCompareSum: a hybrid unsupervised summarization method using salience | ✓ Link | 42.10 | 16.51 | 38.25 | GenCompareSum | |
| On Extractive and Abstractive Neural Document Summarization with Transformer Language Models | ✓ Link | 41.43 | | | TLM-I+E | 2019-09-07 |
| Extractive Summarization as Text Matching | ✓ Link | 41.21 | 14.91 | 36.75 | MatchSum (BERT-base) | 2020-04-19 |
| A Discourse-Aware Attention Model for Abstractive Summarization of Long Documents | ✓ Link | 38.93 | | | Discourse | 2018-04-16 |
| Fastformer: Additive Attention Can Be All You Need | ✓ Link | 38.09 | 15.44 | 34.81 | Fastformer | 2021-08-20 |
| Get To The Point: Summarization with Pointer-Generator Networks | ✓ Link | 35.86 | | | Pntr-Gen-Seq2Seq | 2017-04-14 |