Browse State-of-the-Art › Document Summarization
Document Summarization
226 papers with code · 7 benchmarks · 28 datasets archive 2025-07-28
Automatic Document Summarization is the task of rewriting a document into its shorter form while still retaining its important content. The most popular two paradigms are extractive approaches and abstractive approaches. Extractive approaches generate summaries by extracting parts of the original document (usually sentences), while abstractive methods may generate new words or phrases which are not in the original document.
Description from the archive archive 2025-07-28.
Benchmarks archive 2025-07-28
7 leaderboard tables shown for this task, 7 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.
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 (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
28 datasets whose archive record lists this task, ordered by the archive's paper count.
Subtasks archive 2025-07-28
1 subtask in the archive's task tree.
Parent tasks archive 2025-07-28
Papers archive 2025-07-28
archive papers tagged: 760 · with a code link: 226 · where Syntology ran a sample: 34 (28 with a run with no instrument failure, 6 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (34 of 760 tagged: 28 with a run with no instrument failure, 6 where every run was a failure of Syntology's instrument)
Page 1 of 8: papers 1 to 100 of 760, 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.
-
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).
-
14 Feb 2019 21 repositories listedNatural language processing tasks, such as question answering, machine translation, reading comprehension, and summarization, are typically approached with supervised learning on taskspecific datasets.
-
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…
-
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.
-
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…
-
27 Jun 2023 7 repositories listed Syntology 13 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 0 violated, 4 with no contract checked; 7 where Syntology's instrument failed) · 2 unverified (of 15 harvested samples) · 8 pointer-only (licence)We present Position Interpolation (PI) that extends the context window sizes of RoPE-based pretrained LLMs such as LLaMA models to up to 32768 with minimal fine-tuning (within 1000 steps), while demonstrating strong…
-
14 Nov 2016 7 repositories listed Syntology 6 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; 0 where Syntology's instrument failed) · 1 unverified (of 7 harvested samples)We present SummaRuNNer, a Recurrent Neural Network (RNN) based sequence model for extractive summarization of documents and show that it achieves performance better than or comparable to state-of-the-art.
-
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.
-
30 Jan 2018 4 repositories listedWe show that generating English Wikipedia articles can be approached as a multi- document summarization of source documents.
-
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.
-
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.
-
13 Apr 2020 3 repositories listedRedundancy-aware extractive summarization systems score the redundancy of the sentences to be included in a summary either jointly with their salience information or separately as an additional sentence scoring step.
-
31 May 2019 3 repositories listedThere is thus a crucial gap between sentence selection and fusion to support summarizing by both compressing single sentences and fusing pairs.
-
27 Aug 2018 3 repositories listed Syntology official (archive's flag): 2 ran · 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) · 0 unverified (of 4 harvested samples)We introduce extreme summarization, a new single-document summarization task which does not favor extractive strategies and calls for an abstractive modeling approach.
-
16 Jun 2025 2 repositories listedALST supports training Meta's Llama 8B model with 500K sequence length on a single H100 GPU, 3.
-
3 Oct 2024 2 repositories listedLong-context models (LCMs) have made remarkable strides in recent years, offering users great convenience for handling tasks that involve long context, such as document summarization.
-
3 May 2024 2 repositories listedWe show that the estimated upper bound for extractive summarization increases by 217% in the ROUGE-2 score, when using full content instead of abstracts.
-
1 Oct 2022 2 repositories listedResearch in the biomedical domain is con- stantly challenged by its large amount of ever- evolving textual information.
-
16 Dec 2021 2 repositories listedText clustering methods were traditionally incorporated into multi-document summarization (MDS) as a means for coping with considerable information repetition.
-
16 Oct 2021 2 repositories listedTo the best of our knowledge, Summᴺ is the first multi-stage split-then-summarize framework for long input summarization.
-
13 Apr 2021 2 repositories listed Syntology official (archive's flag): 3 ran · 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)In support of this goal, we release MS^2 (Multi-Document Summarization of Medical Studies), a dataset of over 470k documents and 20k summaries derived from the scientific literature.
-
11 Oct 2020 2 repositories listedRecent work has proposed to summarize arguments by mapping them to a small set of expert-generated key points, where the salience of each key point corresponds to the number of its matching arguments.
-
15 Sep 2020 2 repositories listedA global scoring mechanism is then developed to regulate beam search to generate summaries in a near-global optimal fashion.
-
25 Aug 2020 2 repositories listedWe enlist medical professionals to evaluate generated summaries, and we find that modern summarization systems yield consistently fluent and relevant synopses, but that they are not always factual.
-
26 Jun 2020 2 repositories listed Syntology 15 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 3 honoured, 2 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified (of 18 harvested samples) · 3 pointer-only (licence)The objective noisily captures aspects of paraphrase, translation, multi-document summarization, and information retrieval, allowing for strong zero-shot performance on several tasks.
-
20 May 2020 2 repositories listedGraphs that capture relations between textual units have great benefits for detecting salient information from multiple documents and generating overall coherent summaries.
-
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)It is well known that the standard likelihood training and approximate decoding objectives in neural text generation models lead to less human-like responses for open-ended tasks such as language modeling and story…
-
27 Apr 2020 2 repositories listedMost general-purpose extractive summarization models are trained on news articles, which are short and present all important information upfront.
-
19 Apr 2020 2 repositories listedThis paper creates a paradigm shift with regard to the way we build neural extractive summarization systems.
-
30 Nov 2018 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) · 2 unverified (of 4 harvested samples)We propose TensorFlow Ranking, the first open source library for solving large-scale ranking problems in a deep learning framework.
-
20 Feb 2018 2 repositories listed
-
14 Apr 2017 2 repositories listed
-
1 Apr 2017 2 repositories listed
-
17 Jun 2025 1 repository listed
-
9 Jun 2025 1 repository listed
-
22 May 2025 1 repository listed
-
17 Apr 2025 1 repository listed
-
20 Mar 2025 1 repository listed
-
14 Mar 2025 1 repository listed
-
10 Feb 2025 1 repository listed
-
11 Dec 2024 1 repository listed
-
12 Nov 2024 1 repository listed Syntology official (archive's flag): 3 ran · 4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified (of 5 harvested samples) · 5 pointer-only (licence)
-
31 Oct 2024 1 repository 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)
-
17 Oct 2024 1 repository listed
-
5 Oct 2024 1 repository listed
-
22 Aug 2024 1 repository listed
-
19 Aug 2024 1 repository listed
-
12 Aug 2024 1 repository listed
-
15 Jul 2024 1 repository listed
-
11 Jun 2024 1 repository listed Syntology official: harvested, nothing ran · 0 ran · 1 unverified (of 1 harvested sample) · 1 pointer-only (licence)
-
4 Jun 2024 1 repository listed
-
2 Jun 2024 1 repository listed
-
24 May 2024 1 repository listed
-
23 May 2024 1 repository listed
-
16 May 2024 1 repository listed
-
12 May 2024 1 repository listed
-
25 Apr 2024 1 repository listed
-
15 Apr 2024 1 repository listed
-
25 Mar 2024 1 repository 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)
-
19 Mar 2024 1 repository listed
-
22 Jan 2024 1 repository listed
-
18 Dec 2023 1 repository listed
-
7 Dec 2023 1 repository listed
-
29 Nov 2023 1 repository listed
-
16 Nov 2023 1 repository listed
-
14 Nov 2023 1 repository listed
-
17 Sep 2023 1 repository listed
-
16 Sep 2023 1 repository 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: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified (of 2 harvested samples)
-
14 Sep 2023 1 repository listed Syntology official (archive's flag): 2 ran · 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)
-
25 May 2023 1 repository listed
-
24 May 2023 1 repository listed
-
24 May 2023 1 repository listed
-
23 May 2023 1 repository listed
-
15 May 2023 1 repository listed
-
2 May 2023 1 repository listed
-
26 Apr 2023 1 repository listed Syntology 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) · 11 unverified (of 14 harvested samples)
-
22 Mar 2023 1 repository listed
-
12 Mar 2023 1 repository listed
-
10 Feb 2023 1 repository listed
-
9 Feb 2023 1 repository listed
-
8 Feb 2023 1 repository listed
-
2 Jan 2023 1 repository listed
-
25 Dec 2022 1 repository listed
-
2 Dec 2022 1 repository listed
-
18 Nov 2022 1 repository listed
-
4 Nov 2022 1 repository listed
-
28 Oct 2022 1 repository listed
-
25 Oct 2022 1 repository listed
-
23 Oct 2022 1 repository listed
-
14 Oct 2022 1 repository listed
-
9 Oct 2022 1 repository listed
-
1 Oct 2022 1 repository listed
-
1 Oct 2022 1 repository listed
-
1 Oct 2022 1 repository listed
-
1 Oct 2022 1 repository listed
-
1 Oct 2022 1 repository listed
-
1 Oct 2022 1 repository listed
-
17 Aug 2022 1 repository listed
-
1 Aug 2022 1 repository listed
-
3 Jul 2022 1 repository listed
Syntology lines on 20 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