Browse State-of-the-Art › Abstractive Text Summarization
Abstractive Text Summarization
362 papers with code · 15 benchmarks · 52 datasets archive 2025-07-28
Abstractive Text Summarization is the task of generating a short and concise summary that captures the salient ideas of the source text. The generated summaries potentially contain new phrases and sentences that may not appear in the source text.
Source: Generative Adversarial Network for Abstractive Text Summarization
Image credit: Abstractive Text Summarization using Sequence-to-sequence RNNs and Beyond
Description from the archive archive 2025-07-28.
Benchmarks archive 2025-07-28
20 leaderboard tables shown for this task, 15 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted. 10 shown of 20 until expanded.
Syntology 4 newer papers were judged to report on this task's benchmarks so far (Claude Sonnet 4.5, reading their tables: a model's judgement, not a result; 0 placed): CNN / Daily Mail (3 judged, 0 placed), CNN/Daily Mail (4 judged, 0 placed). Drawn from 8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read).
Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. Each line reads “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. When the archive marks a repository official for the row's paper, the line starts with that repository's state (“official” is 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. A dash means no Syntology record for that paper, not a recorded non-run. Each “ran” line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
Libraries
Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.
Datasets archive 2025-07-28
52 datasets whose archive record lists this task, ordered by the archive's paper count. 30 shown of 52 until expanded.
Subtasks archive 2025-07-28
3 subtasks in the archive's task tree.
Parent tasks archive 2025-07-28
Papers archive 2025-07-28
archive papers tagged: 846 · with a code link: 362 · where Syntology ran a sample: 77 (62 with a run with no instrument failure, 15 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (77 of 846 tagged: 62 with a run with no instrument failure, 15 where every run was a failure of Syntology's instrument)
Page 1 of 9: papers 1 to 100 of 846, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.
Papers without a page here are shown as plain text. A Syntology line reads “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 figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. 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); hover it for the repositories the samples that ran came from. The first sentence of the abstract is shown for the first 30 papers; every abstract is on its paper's page.
-
12 Jun 2017 595 repositories listed Syntology official: no sample here; runs from other or unrecorded repositories · 610 ran (of which 293 constructed an object rather than computing a result; 529 with no instrument failure: 45 honoured, 15 violated, 469 with no contract checked; 81 where Syntology's instrument failed) · 336 unverified (of 946 harvested samples) · 451 pointer-only (licence)The dominant sequence transduction models are based on complex recurrent or convolutional neural networks in an encoder-decoder configuration.
-
29 Oct 2019 47 repositories listed Syntology 40 ran (of which 7 constructed an object rather than computing a result; 30 with no instrument failure: 1 honoured, 2 violated, 27 with no contract checked; 10 where Syntology's instrument failed) · 13 unverified (of 53 harvested samples) · 13 pointer-only (licence)We evaluate a number of noising approaches, finding the best performance by both randomly shuffling the order of the original sentences and using a novel in-filling scheme, where spans of text are replaced with a single…
-
14 Apr 2017 39 repositories listed Syntology official: no sample here; runs from other or unrecorded repositories · 30 ran (of which 11 constructed an object rather than computing a result; 25 with no instrument failure: 4 honoured, 2 violated, 19 with no contract checked; 5 where Syntology's instrument failed) · 34 unverified (of 64 harvested samples) · 44 pointer-only (licence)Neural sequence-to-sequence models have provided a viable new approach for abstractive text summarization (meaning they are not restricted to simply selecting and rearranging passages from the original text).
-
18 Dec 2019 19 repositories listed Syntology 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)Recent work pre-training Transformers with self-supervised objectives on large text corpora has shown great success when fine-tuned on downstream NLP tasks including text summarization.
-
22 Aug 2019 19 repositories listed Syntology community repositories only · 13 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 1 violated, 9 with no contract checked; 3 where Syntology's instrument failed) · 8 unverified (of 21 harvested samples) · 5 pointer-only (licence)For abstractive summarization, we propose a new fine-tuning schedule which adopts different optimizers for the encoder and the decoder as a means of alleviating the mismatch between the two (the former is pretrained…
-
11 May 2017 10 repositories listedWe introduce a neural network model with a novel intra-attention that attends over the input and continuously generated output separately, and a new training method that combines standard supervised word prediction and…
-
8 May 2019 9 repositories listedThis paper presents a new Unified pre-trained Language Model (UniLM) that can be fine-tuned for both natural language understanding and generation tasks.
-
28 Jun 2021 8 repositories listed Syntology community repositories only · 4 ran (of which 2 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)Dropout is a powerful and widely used technique to regularize the training of deep neural networks.
-
18 Mar 2021 8 repositories listed Syntology community repositories only · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample)On a wide range of tasks across NLU, conditional and unconditional generation, GLM outperforms BERT, T5, and GPT given the same model sizes and data, and achieves the best performance from a single pretrained model with…
-
26 Jan 2020 5 repositories listedCurrent pre-training works in natural language generation pay little attention to the problem of exposure bias on downstream tasks.
-
13 Jan 2020 5 repositories listedThis paper presents a new sequence-to-sequence pre-training model called ProphetNet, which introduces a novel self-supervised objective named future n-gram prediction and the proposed n-stream self-attention mechanism.
-
3 Sep 2019 5 repositories listed Syntology official (archive's flag): 5 ran · 8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified (of 11 harvested samples) · 1 pointer-only (licence)We propose LaserTagger - a sequence tagging approach that casts text generation as a text editing task.
-
5 Dec 2018 5 repositories listed Syntology community repositories only · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified (of 2 harvested samples)As part of this survey, we also develop an open source library, namely, Neural Abstractive Text Summarizer (NATS) toolkit, for the abstractive text summarization.
-
31 Aug 2018 5 repositories listed Syntology official (archive's flag): 5 ran · 5 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified (of 6 harvested samples)We use this selector as a bottom-up attention step to constrain the model to likely phrases.
-
15 Dec 2021 4 repositories listed Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample) · 1 pointer-only (licence)Recent work has shown that either (1) increasing the input length or (2) increasing model size can improve the performance of Transformer-based neural models.
-
30 Apr 2020 4 repositories listed Syntology official (archive's flag): 5 ran · 17 ran (of which 1 constructed an object rather than computing a result; 10 with no instrument failure: 4 honoured, 0 violated, 6 with no contract checked; 7 where Syntology's instrument failed) · 2 unverified (of 19 harvested samples) · 4 pointer-only (licence)We introduce TLDR generation, a new form of extreme summarization, for scientific papers.
-
28 Oct 2019 4 repositories listed Syntology official (archive's flag): 2 ran · 3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples)Currently used metrics for assessing summarization algorithms do not account for whether summaries are factually consistent with source documents.
-
25 Feb 2019 4 repositories listed Syntology 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample) · 1 pointer-only (licence)For the decoder, there are two stages in our model, in the first stage, we use a Transformer-based decoder to generate a draft output sequence.
-
14 May 2018 4 repositories listedWe introduce a novel graph-based framework for abstractive meeting speech summarization that is fully unsupervised and does not rely on any annotations.
-
10 May 2018 4 repositories listed Syntology official (archive's flag): 1 ran · 3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified (of 7 harvested samples)To tackle the problem, we propose a global encoding framework, which controls the information flow from the encoder to the decoder based on the global information of the source context.
-
19 Feb 2016 4 repositories listed Syntology 5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified (of 6 harvested samples)In this work, we model abstractive text summarization using Attentional Encoder-Decoder Recurrent Neural Networks, and show that they achieve state-of-the-art performance on two different corpora.
-
24 Oct 2022 3 repositories listed Syntology official (archive's flag): 8 ran · 10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified (of 12 harvested samples) · 1 pointer-only (licence)Despite significant progress in the quality of language generated from abstractive summarization models, these models still exhibit the tendency to hallucinate, i. e., output content not supported by the source document.
-
13 Apr 2022 3 repositories listedDespite recent improvements in abstractive summarization, most current approaches generate summaries that are not factually consistent with the source document, severely restricting their trust and usage in real-world…
-
31 Mar 2022 3 repositories listed Syntology community repositories only · 7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified (of 10 harvested samples)Abstractive summarization models are commonly trained using maximum likelihood estimation, which assumes a deterministic (one-point) target distribution in which an ideal model will assign all the probability mass to…
-
1 Feb 2022 3 repositories listed Syntology official (archive's flag): 10 ran · 19 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 3 honoured, 1 violated, 10 with no contract checked; 5 where Syntology's instrument failed) · 6 unverified (of 25 harvested samples) · 15 pointer-only (licence)Automatic and human evaluations show that, in comparison to nucleus and top-k sampling, locally typical sampling offers competitive performance (in both abstractive summarization and story generation) in terms of…
-
16 Oct 2021 3 repositories listed Syntology official (archive's flag): 4 ran · 7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified (of 7 harvested samples)We introduce PRIMERA, a pre-trained model for multi-document representation with a focus on summarization that reduces the need for dataset-specific architectures and large amounts of fine-tuning labeled data.
-
20 Sep 2021 3 repositories listedWe present BARTpho with two versions, BARTpho-syllable and BARTpho-word, which are the first public large-scale monolingual sequence-to-sequence models pre-trained for Vietnamese.
-
19 Sep 2021 3 repositories listedWe study generating abstractive summaries that are faithful and factually consistent with the given articles.
-
9 Apr 2021 3 repositories listed Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified (of 3 harvested samples) · 3 pointer-only (licence)Recent pre-trained abstractive summarization systems have started to achieve credible performance, but a major barrier to their use in practice is their propensity to output summaries that are not faithful to the input…
-
14 Nov 2020 3 repositories listed Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample) · 1 pointer-only (licence)Finally, we present a search engine for this dataset which is utilized extensively by members of the National Speech and Debate Association today.
-
1 Nov 2020 3 repositories listed
-
6 Aug 2020 3 repositories listed
-
4 Apr 2020 3 repositories listed
-
28 Feb 2020 3 repositories listed Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample)
-
6 Nov 2019 3 repositories listed
-
31 May 2019 3 repositories listed
-
29 Jan 2019 3 repositories listed
-
28 May 2018 3 repositories listed Syntology official (archive's flag): 1 ran · 3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples) · 2 pointer-only (licence)
-
24 May 2018 3 repositories listed Syntology official (archive's flag): 12 ran · 16 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 2 honoured, 0 violated, 13 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified (of 17 harvested samples) · 2 pointer-only (licence)
-
16 Apr 2018 3 repositories listed Syntology official (archive's flag): 6 ran · 7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 7 unverified (of 14 harvested samples)
-
22 Dec 2024 2 repositories listed
-
14 Dec 2023 2 repositories listed
-
9 Oct 2023 2 repositories listed Syntology official (archive's flag): 3 ran · 3 ran (of which 1 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) · 6 pointer-only (licence)
-
4 Aug 2023 2 repositories listed Syntology official (archive's flag): 12 ran · 12 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified (of 14 harvested samples) · 3 pointer-only (licence)
-
1 Aug 2023 2 repositories listed
-
20 Dec 2022 2 repositories listed
-
19 Dec 2022 2 repositories listed
-
8 Aug 2022 2 repositories listed
-
20 May 2022 2 repositories listed
-
30 Mar 2022 2 repositories listed Syntology official (archive's flag): 1 ran · 5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified (of 5 harvested samples) · 3 pointer-only (licence)
-
29 Jan 2022 2 repositories listed
-
1 Dec 2021 2 repositories listed Syntology official (archive's flag): 3 ran · 7 ran (of which 1 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified (of 8 harvested samples) · 4 pointer-only (licence)
-
16 Oct 2021 2 repositories listed
-
15 Oct 2021 2 repositories listed
-
31 Aug 2021 2 repositories listed
-
26 Aug 2021 2 repositories listed
-
25 Jun 2021 2 repositories listed
-
25 Jun 2021 2 repositories listed Syntology official: no sample here; runs from other or unrecorded repositories · 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified (of 3 harvested samples) · 3 pointer-only (licence)
-
3 Jun 2021 2 repositories listed Syntology 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)
-
18 May 2021 2 repositories listed Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample)
-
Understanding Factuality in Abstractive Summarization with FRANK: A Benchmark for Factuality Metrics27 Apr 2021 2 repositories listed Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples)
-
18 Apr 2021 2 repositories listed
-
15 Apr 2021 2 repositories listed Syntology official (archive's flag): 2 ran · 2 ran (of which 0 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) · 0 unverified (of 2 harvested samples)
-
26 Jan 2021 2 repositories listed
-
5 Nov 2020 2 repositories listed
-
24 Oct 2020 2 repositories listed
-
15 Sep 2020 2 repositories listed
-
25 Aug 2020 2 repositories listed
-
21 Aug 2020 2 repositories listed
-
7 May 2020 2 repositories listed
-
2 May 2020 2 repositories listed Syntology official: no sample here; runs from other or unrecorded repositories · 2 ran (of which 0 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) · 0 unverified (of 2 harvested samples)
-
24 Apr 2020 2 repositories listed
-
14 Apr 2020 2 repositories listed
-
8 Apr 2020 2 repositories listed
-
27 Nov 2019 2 repositories listed
-
23 Nov 2019 2 repositories listed
-
2 Oct 2019 2 repositories listed
-
4 Sep 2019 2 repositories listed Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples)
-
2 Aug 2019 2 repositories listed
-
1 Jun 2019 2 repositories listed
-
21 May 2019 2 repositories listed
-
2 Apr 2019 2 repositories listed
-
20 Oct 2018 2 repositories listed
-
12 Oct 2018 2 repositories listed Syntology community repositories only · 4 ran (of which 0 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) · 1 unverified (of 5 harvested samples)
-
17 Dec 2017 2 repositories listed
-
26 Apr 2017 2 repositories listed
-
22 May 2025 1 repository listed
-
20 May 2025 1 repository listed
-
16 May 2025 1 repository listed
-
11 May 2025 1 repository listed
-
7 May 2025 1 repository listed
-
14 Mar 2025 1 repository listed
-
21 Feb 2025 1 repository listed
-
7 Feb 2025 1 repository listed
-
7 Feb 2025 1 repository listed
-
12 Nov 2024 1 repository listed
-
21 Oct 2024 1 repository listed
-
11 Oct 2024 1 repository listed
-
8 Oct 2024 1 repository listed
-
4 Oct 2024 1 repository listed Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples) · 3 pointer-only (licence)
Syntology lines on 39 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
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