Methods › Natural Language Processing › Transformers › PEGASUS
PEGASUS
Introduced by Jingqing Zhang et al. in PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
PEGASUS proposes a transformer-based model for abstractive summarization. It uses a special self-supervised pre-training objective called gap-sentences generation (GSG) that's designed to perform well on summarization-related downstream tasks. As reported in the paper, "both GSG and MLM are applied simultaneously to this example as pre-training objectives. Originally there are three sentences. One sentence is masked with [MASK1] and used as target generation text (GSG). The other two sentences remain in the input, but some tokens are randomly masked by [MASK2]."
In Syntology about another paper, arXiv:2402.10636: no code under this exact name (no_code; paper_only). About another paper: this answer is about arXiv:2402.10636, while the archive credits arXiv:1912.08777, so it does not say whether this method has code.
From the lookup's note on this name: The same name also belongs to the paper “PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization” (arXiv:1912.08777, 2,560 citations), which the lookup finds cited far more than the paper this answer is about (8 citations), so this answer may be about a different sense of the name. For arXiv:1912.08777: its page on this site · ask the lookup about it.
Origin paper of this answer, arXiv:2402.10636 (its page on Syntology).
Syntology's have check for this name (free, it answers coverage only), read 2026-10-05; ask it again live. A level is the served verification level of that one answer; nothing here is summed across methods.
Papers archive 2025-07-28
archive papers tagged: 53 · with a code link: 20 · where Syntology ran a sample: 5 (5 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (5 of 53 tagged: 5 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 53 of 53, newest first by the archive's date (ties by slug), in archive order.
Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code, as “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. It is per sample and not a correctness claim. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from.
-
Pegasus: A Universal Framework for Scalable Deep Learning Inference on the Dataplane 6 Jun 2025 · 0 repositories · arXiv:2506.05779
-
QUAD-LLM-MLTC: Large Language Models Ensemble Learning for Healthcare Text Multi-Label Classification 20 Feb 2025 · 0 repositories · arXiv:2502.14189
-
Implementing Large Quantum Boltzmann Machines as Generative AI Models for Dataset Balancing 5 Feb 2025 · 0 repositories · arXiv:2502.03086
-
Extract-and-Abstract: Unifying Extractive and Abstractive Summarization within Single Encoder-Decoder Framework 18 Sep 2024 · 0 repositories · arXiv:2409.11827
-
GLIMMER: Incorporating Graph and Lexical Features in Unsupervised Multi-Document Summarization 19 Aug 2024 · 1 repository · arXiv:2408.10115
-
BioLay_AK_SS at BioLaySumm: Domain Adaptation by Two-Stage Fine-Tuning of Large Language Models used for Biomedical Lay Summary Generation 16 Aug 2024 · 0 repositories
-
Factual Dialogue Summarization via Learning from Large Language Models 20 Jun 2024 · 0 repositories · arXiv:2406.14709
-
Comparing Quantum Annealing and Spiking Neuromorphic Computing for Sampling Binary Sparse Coding QUBO Problems 30 May 2024 · 0 repositories · arXiv:2405.20525
-
Evaluating Text Summaries Generated by Large Language Models Using OpenAI's GPT 7 May 2024 · 0 repositories · arXiv:2405.04053
-
MEDVOC: Vocabulary Adaptation for Fine-tuning Pre-trained Language Models on Medical Text Summarization 7 May 2024 · 1 repository · arXiv:2405.04163Syntology official (archive's flag): 8 ran · 8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 2 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified (of 9 harvested samples) · 9 pointer-only (licence)
-
Analysis of Multidomain Abstractive Summarization Using Salience Allocation 19 Feb 2024 · 0 repositories · arXiv:2402.11955
-
PEGASUS: Personalized Generative 3D Avatars with Composable Attributes 16 Feb 2024 · 0 repositories · arXiv:2402.10636
-
Source Identification in Abstractive Summarization 7 Feb 2024 · 1 repository · arXiv:2402.04677
-
PEGASUS: Physically Enhanced Gaussian Splatting Simulation System for 6DoF Object Pose Dataset Generation 4 Jan 2024 · 1 repository · arXiv:2401.02281
-
Revisiting Zero-Shot Abstractive Summarization in the Era of Large Language Models from the Perspective of Position Bias 3 Jan 2024 · 1 repository · arXiv:2401.01989
-
Harnessing the Power of Prompt-based Techniques for Generating School-Level Questions using Large Language Models 2 Dec 2023 · 1 repository · arXiv:2312.01032
-
FaMeSumm: Investigating and Improving Faithfulness of Medical Summarization 3 Nov 2023 · 1 repository · arXiv:2311.02271Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified (of 6 harvested samples)
-
Abstractive Summarization of Large Document Collections Using GPT 9 Oct 2023 · 0 repositories · arXiv:2310.05690
-
Minimum-length chain embedding for the phase unwrapping problem on D-Wave's advantage architecture 19 Sep 2023 · 0 repositories · arXiv:2309.10296
-
Automatic Personalized Impression Generation for PET Reports Using Large Language Models 18 Sep 2023 · 2 repositories · arXiv:2309.10066
-
Multi-document Summarization: A Comparative Evaluation 10 Sep 2023 · 0 repositories · arXiv:2309.04951
-
"Beware of deception": Detecting Half-Truth and Debunking it through Controlled Claim Editing 15 Aug 2023 · 0 repositories · arXiv:2308.07973
-
Summarization from Leaderboards to Practice: Choosing A Representation Backbone and Ensuring Robustness 18 Jun 2023 · 0 repositories · arXiv:2306.10555
-
pyBibX -- A Python Library for Bibliometric and Scientometric Analysis Powered with Artificial Intelligence Tools 27 Apr 2023 · 1 repository · arXiv:2304.14516
-
Summaries as Captions: Generating Figure Captions for Scientific Documents with Automated Text Summarization 23 Feb 2023 · 0 repositories · arXiv:2302.12324
-
Unsupervised Summarization Re-ranking 19 Dec 2022 · 2 repositories · arXiv:2212.09593
-
Implementing Deep Learning-Based Approaches for Article Summarization in Indian Languages 12 Dec 2022 · 0 repositories · arXiv:2212.05702
-
Investigating Efficiently Extending Transformers for Long Input Summarization 8 Aug 2022 · 2 repositories · arXiv:2208.04347
-
Indian Legal Text Summarization: A Text Normalisation-based Approach 13 Jun 2022 · 0 repositories · arXiv:2206.06238
-
Medical Scientific Table-to-Text Generation with Human-in-the-Loop under the Data Sparsity Constraint 24 May 2022 · 0 repositories · arXiv:2205.12368
-
SummaReranker: A Multi-Task Mixture-of-Experts Re-ranking Framework for Abstractive Summarization 13 Mar 2022 · 1 repository · arXiv:2203.06569Syntology official (archive's flag): 2 ran · 2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; every one of the 2 samples that ran constructed an object rather than computing a result (of 3 harvested samples)
-
FRSUM: Towards Faithful Abstractive Summarization via Enhancing Factual Robustness 16 Nov 2021 · 0 repositories
-
Generation of News Articles from Tweets : An Experiment 16 Nov 2021 · 0 repositories
-
SummaReranker: A Multi-Task Mixture-of-Experts Re-ranking Framework for Abstractive Summarization 16 Nov 2021 · 0 repositories
-
Adding more data does not always help: A study in medical conversation summarization with PEGASUS 15 Nov 2021 · 1 repository · arXiv:2111.07564
-
Should We Trust This Summary? Bayesian Abstractive Summarization to The Rescue 16 Oct 2021 · 0 repositories
-
CLIFF: Contrastive Learning for Improving Faithfulness and Factuality in Abstractive Summarization 19 Sep 2021 · 3 repositories · arXiv:2109.09209
-
Noobs at Semeval-2021 Task 4: Masked Language Modeling for abstract answer prediction 1 Aug 2021 · 0 repositories
-
AgreeSum: Agreement-Oriented Multi-Document Summarization 4 Jun 2021 · 0 repositories · arXiv:2106.02278
-
SimCLS: A Simple Framework for Contrastive Learning of Abstractive Summarization 3 Jun 2021 · 2 repositories · arXiv:2106.01890Syntology official (archive's flag): 1 ran · 4 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified (of 6 harvested samples) · 1 pointer-only (licence)
-
BDKG at MEDIQA 2021: System Report for the Radiology Report Summarization Task 1 Jun 2021 · 0 repositories
-
MNLP at MEDIQA 2021: Fine-Tuning PEGASUS for Consumer Health Question Summarization 1 Jun 2021 · 0 repositories
-
NCUEE-NLP at MEDIQA 2021: Health Question Summarization Using PEGASUS Transformers 1 Jun 2021 · 0 repositories
-
SB_NITK at MEDIQA 2021: Leveraging Transfer Learning for Question Summarization in Medical Domain 1 Jun 2021 · 0 repositories
-
WBI at MEDIQA 2021: Summarizing Consumer Health Questions with Generative Transformers 1 Jun 2021 · 0 repositories
-
Should We Trust This Summary? Bayesian Abstractive Summarization to The Rescue 21 May 2021 · 0 repositories · arXiv:2105.10155
-
Quiz-Style Question Generation for News Stories 18 Feb 2021 · 2 repositories · arXiv:2102.09094
-
6-Layer Model for a Structured Description and Categorization of Urban Traffic and Environment 9 Dec 2020 · 0 repositories · arXiv:2012.06319
-
Flight of the PEGASUS? Comparing Transformers on Few-shot and Zero-shot Multi-document Abstractive Summarization 1 Dec 2020 · 1 repository
-
AUTH @ CLSciSumm 20, LaySumm 20, LongSumm 20 1 Nov 2020 · 0 repositories
-
Pre-trained Summarization Distillation 24 Oct 2020 · 1 repository · arXiv:2010.13002
-
Understanding Neural Abstractive Summarization Models via Uncertainty 15 Oct 2020 · 1 repository · arXiv:2010.07882
-
PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization 18 Dec 2019 · 19 repositories · arXiv:1912.08777Syntology official (archive's flag): 7 ran · 16 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 0 honoured, 0 violated, 15 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified (of 19 harvested samples)
Tasks archive 2025-07-28
20 shown of 62 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections