{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/document-summarization","name":"Document Summarization","slug":"document-summarization","description_markdown":"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.\n\n\n<span class=\"description-source\">Source: [HIBERT: Document Level Pre-training of Hierarchical Bidirectional Transformers for Document Summarization ](https://arxiv.org/abs/1905.06566)</span>","categories":[{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":760,"papers_with_code":226,"benchmarks":7,"benchmark_tables_in_archive":7,"benchmark_tables_shown":7,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":28,"subtasks":1,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/document-summarization-on-cnn-daily-mail","slug":"document-summarization-on-cnn-daily-mail","dataset":"CNN / Daily Mail","dataset_url":"/dataset/cnn-daily-mail-1","rows_in_archive":26,"metrics":["ROUGE-1","ROUGE-2","ROUGE-L","PPL"],"first_row_in_archive_order":{"model":"Scrambled code + broken (alter)","paper_title":"Universal Evasion Attacks on Summarization Scoring","paper_url":"/paper/universal-evasion-attacks-on-summarization","paper_date":"2022-10-25","arxiv_id":"2210.14260","code_links":[{"title":"cestwc/universal-evasion","url":"https://github.com/cestwc/universal-evasion"}],"syntology":null}},{"leaderboard":"/sota/document-summarization-on-howsumm-step","slug":"document-summarization-on-howsumm-step","dataset":"HowSumm-Step","dataset_url":"/dataset/howsumm","rows_in_archive":11,"metrics":["ROUGE-1"],"first_row_in_archive_order":{"model":"LexRank (query: step title)","paper_title":"HowSumm: A Multi-Document Summarization Dataset Derived from WikiHow Articles","paper_url":"/paper/howsumm-a-multi-document-summarization","paper_date":"2021-10-07","arxiv_id":"2110.03179","code_links":[{"title":"odelliab/HowSumm","url":"https://github.com/odelliab/HowSumm"}],"syntology":null}},{"leaderboard":"/sota/document-summarization-on-howsumm-method","slug":"document-summarization-on-howsumm-method","dataset":"HowSumm-Method","dataset_url":"/dataset/howsumm","rows_in_archive":9,"metrics":["ROUGE-1"],"first_row_in_archive_order":{"model":"LexRank (query: method + article + steps titles)","paper_title":"HowSumm: A Multi-Document Summarization Dataset Derived from WikiHow Articles","paper_url":"/paper/howsumm-a-multi-document-summarization","paper_date":"2021-10-07","arxiv_id":"2110.03179","code_links":[{"title":"odelliab/HowSumm","url":"https://github.com/odelliab/HowSumm"}],"syntology":null}},{"leaderboard":"/sota/document-summarization-on-arxiv","slug":"document-summarization-on-arxiv","dataset":"Arxiv HEP-TH citation graph","dataset_url":"/dataset/arxiv","rows_in_archive":1,"metrics":["ROUGE-1"],"first_row_in_archive_order":{"model":"DeepPyramidion","paper_title":"Sparsifying Transformer Models with Trainable Representation Pooling","paper_url":"/paper/sparsifying-transformer-models-with-trainable","paper_date":"2021-11-16","arxiv_id":null,"code_links":[],"syntology":null}},{"leaderboard":"/sota/document-summarization-on-arxiv-summarization","slug":"document-summarization-on-arxiv-summarization","dataset":"arXiv Summarization Dataset","dataset_url":"/dataset/arxiv-summarization-dataset","rows_in_archive":1,"metrics":["Rouge-2"],"first_row_in_archive_order":{"model":"DeepPyramidion","paper_title":"Sparsifying Transformer Models with Trainable Representation Pooling","paper_url":"/paper/sparsifying-transformer-models-with-trainable","paper_date":"2021-11-16","arxiv_id":null,"code_links":[],"syntology":null}},{"leaderboard":"/sota/document-summarization-on-bbc-xsum","slug":"document-summarization-on-bbc-xsum","dataset":"BBC XSum","dataset_url":null,"rows_in_archive":1,"metrics":["ROUGE-1","ROUGE-2","ROUGE-L"],"first_row_in_archive_order":{"model":"BigBird-Pegasus","paper_title":"Big Bird: Transformers for Longer Sequences","paper_url":"/paper/big-bird-transformers-for-longer-sequences","paper_date":"2020-07-28","arxiv_id":"2007.14062","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"tensorflow/models","url":"https://github.com/tensorflow/models/tree/master/official/nlp/projects/bigbird"},{"title":"PaddlePaddle/PaddleNLP","url":"https://github.com/PaddlePaddle/PaddleNLP/tree/develop/paddlenlp/transformers/bigbird"},{"title":"facebookresearch/xformers","url":"https://github.com/facebookresearch/xformers"},{"title":"google-research/bigbird","url":"https://github.com/google-research/bigbird"},{"title":"monologg/kobigbird","url":"https://github.com/monologg/kobigbird"},{"title":"mim-solutions/bert_for_longer_texts","url":"https://github.com/mim-solutions/bert_for_longer_texts"},{"title":"mim-solutions/roberta_for_longer_texts","url":"https://github.com/mim-solutions/roberta_for_longer_texts"},{"title":"sajjjadayobi/ParsBigBird","url":"https://github.com/sajjjadayobi/ParsBigBird"},{"title":"thefonseca/factorsum","url":"https://github.com/thefonseca/factorsum"},{"title":"2024-MindSpore-1/Code2","url":"https://github.com/2024-MindSpore-1/Code2/tree/main/model-1/big_bird"},{"title":"sergeykramp/mthesis-bigbird-embeddings","url":"https://github.com/sergeykramp/mthesis-bigbird-embeddings"},{"title":"pwc-1/Paper-8","url":"https://github.com/pwc-1/Paper-8/tree/main/big_bird"},{"title":"pwc-1/Paper-8","url":"https://github.com/pwc-1/Paper-8/tree/main/bigbird_pegasus"}],"syntology":{"n":15,"n_ran":10,"n_constructed":1,"n_ran_checked":2,"n_instrument":8,"n_unverified":5,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":11,"phrase":"10 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 8 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/big-bird-transformers-for-longer-sequences#ran","syntology_url":"https://syntology.ai/paper/2007.14062","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.14062"}},"official":{"repos":["google-research/bigbird"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed","official"]}}}},{"leaderboard":"/sota/document-summarization-on-wikilingua-tr-en","slug":"document-summarization-on-wikilingua-tr-en","dataset":"WikiLingua (tr->en)","dataset_url":"/dataset/wikilingua","rows_in_archive":1,"metrics":["Rouge-L"],"first_row_in_archive_order":{"model":"DOCmT5","paper_title":"DOCmT5: Document-Level Pretraining of Multilingual Language Models","paper_url":"/paper/docmt5-document-level-pretraining-of","paper_date":"2021-12-16","arxiv_id":"2112.08709","code_links":[],"syntology":null}}],"datasets":[{"url":"/dataset/cnn-daily-mail-1","name":"CNN/Daily Mail","full_name":"CNN/Daily Mail","num_papers_in_archive":530},{"url":"/dataset/new-york-times-annotated-corpus","name":"New York Times Annotated Corpus","full_name":"","num_papers_in_archive":262},{"url":"/dataset/multi-news","name":"Multi-News","full_name":"Multi-News","num_papers_in_archive":122},{"url":"/dataset/newsroom","name":"NEWSROOM","full_name":"CORNELL NEWSROOM","num_papers_in_archive":107},{"url":"/dataset/wikisum","name":"WikiSum","full_name":"WikiSum","num_papers_in_archive":54},{"url":"/dataset/wikilingua","name":"WikiLingua","full_name":"","num_papers_in_archive":52},{"url":"/dataset/booksum","name":"BookSum","full_name":"","num_papers_in_archive":39},{"url":"/dataset/arxiv","name":"Arxiv HEP-TH citation graph","full_name":"","num_papers_in_archive":35},{"url":"/dataset/wcep","name":"WCEP","full_name":"Wikipedia Current Events Portal","num_papers_in_archive":31},{"url":"/dataset/aeslc","name":"AESLC","full_name":"","num_papers_in_archive":22},{"url":"/dataset/scisummnet","name":"ScisummNet","full_name":"","num_papers_in_archive":20},{"url":"/dataset/arxiv-summarization-dataset","name":"arXiv Summarization Dataset","full_name":"","num_papers_in_archive":13},{"url":"/dataset/aquamuse","name":"aquamuse","full_name":"","num_papers_in_archive":11},{"url":"/dataset/multi-xscience","name":"Multi-XScience","full_name":null,"num_papers_in_archive":10},{"url":"/dataset/cqasumm","name":"CQASUMM","full_name":"","num_papers_in_archive":9},{"url":"/dataset/eur-lex-sum","name":"EUR-Lex-Sum","full_name":"","num_papers_in_archive":8},{"url":"/dataset/oposum","name":"OpoSum","full_name":"","num_papers_in_archive":7},{"url":"/dataset/talksumm","name":"TalkSumm","full_name":"TalkSumm","num_papers_in_archive":6},{"url":"/dataset/matinf","name":"MATINF","full_name":"Maternal and Infant Dataset","num_papers_in_archive":5},{"url":"/dataset/facetsum","name":"FacetSum","full_name":"","num_papers_in_archive":4},{"url":"/dataset/wikipedia-generation","name":"Wikipedia Generation","full_name":"Wikipedia Generation","num_papers_in_archive":4},{"url":"/dataset/elsevier-oa-cc-by","name":"Elsevier OA CC-BY","full_name":"","num_papers_in_archive":2},{"url":"/dataset/findsum","name":"FINDSum","full_name":"Financial Report Document Summarization","num_papers_in_archive":2},{"url":"/dataset/gamewikisum","name":"GameWikiSum","full_name":null,"num_papers_in_archive":1},{"url":"/dataset/howsumm","name":"HowSumm","full_name":"","num_papers_in_archive":1},{"url":"/dataset/pmc-sa","name":"PMC-SA","full_name":"PMC Structured Abstracts","num_papers_in_archive":1},{"url":"/dataset/qbsum","name":"QBSUM","full_name":"","num_papers_in_archive":1},{"url":"/dataset/subsume","name":"SubSumE","full_name":"","num_papers_in_archive":1}],"subtasks":[{"url":"/task/email-thread-summarization","name":"Email Thread Summarization"}],"parent_tasks":[{"url":"/task/text-summarization","name":"Text Summarization"}],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":8,"rows_per_page":100,"shown":100,"of":760,"of_with_code":226,"tagged_in_all":760,"counts":{"archive_papers_tagged":760,"with_a_code_link":226,"where_syntology_ran_a_sample":34,"not_listed_spam_title":0,"listed":760,"listed_where_code_ran":34,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":28,"every_run_a_failure_of_syntologys_instrument":6,"listed_with_a_run_with_no_instrument_failure":28,"listed_every_run_a_failure_of_syntologys_instrument":6,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/get-to-the-point-summarization-with-pointer","slug":"get-to-the-point-summarization-with-pointer","title":"Get To The Point: Summarization with Pointer-Generator Networks","date":"2017-04-14","arxiv_id":"1704.04368","repositories_listed":39,"syntology":{"n":64,"n_ran":30,"n_constructed":11,"n_ran_checked":25,"n_instrument":5,"n_unverified":34,"n_honours":4,"n_violates":2,"n_no_contract":19,"n_pointer_only":44,"phrase":"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","sample_list":"/paper/get-to-the-point-summarization-with-pointer#ran","syntology_url":"https://syntology.ai/paper/1704.04368","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1704.04368"}},"official":{"repos":["abisee/pointer-generator"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]}}},{"url":"/paper/language-models-are-unsupervised-multitask","slug":"language-models-are-unsupervised-multitask","title":"Language Models are Unsupervised Multitask Learners","date":"2019-02-14","arxiv_id":null,"repositories_listed":21,"syntology":null},{"url":"/paper/text-summarization-with-pretrained-encoders","slug":"text-summarization-with-pretrained-encoders","title":"Text Summarization with Pretrained Encoders","date":"2019-08-22","arxiv_id":"1908.08345","repositories_listed":19,"syntology":{"n":21,"n_ran":13,"n_constructed":0,"n_ran_checked":10,"n_instrument":3,"n_unverified":8,"n_honours":0,"n_violates":1,"n_no_contract":9,"n_pointer_only":5,"phrase":"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","sample_list":"/paper/text-summarization-with-pretrained-encoders#ran","syntology_url":"https://syntology.ai/paper/1908.08345","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.08345"}},"official":{"repos":["nlpyang/PreSumm"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/unified-language-model-pre-training-for","slug":"unified-language-model-pre-training-for","title":"Unified Language Model Pre-training for Natural Language Understanding and Generation","date":"2019-05-08","arxiv_id":"1905.03197","repositories_listed":9,"syntology":null},{"url":"/paper/all-nlp-tasks-are-generation-tasks-a-general","slug":"all-nlp-tasks-are-generation-tasks-a-general","title":"GLM: General Language Model Pretraining with Autoregressive Blank Infilling","date":"2021-03-18","arxiv_id":"2103.10360","repositories_listed":8,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"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","sample_list":"/paper/all-nlp-tasks-are-generation-tasks-a-general#ran","syntology_url":"https://syntology.ai/paper/2103.10360","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.10360"}},"official":{"repos":["THUDM/GLM"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/extending-context-window-of-large-language","slug":"extending-context-window-of-large-language","title":"Extending Context Window of Large Language Models via Positional Interpolation","date":"2023-06-27","arxiv_id":"2306.15595","repositories_listed":7,"syntology":{"n":15,"n_ran":13,"n_constructed":0,"n_ran_checked":6,"n_instrument":7,"n_unverified":2,"n_honours":2,"n_violates":0,"n_no_contract":4,"n_pointer_only":8,"phrase":"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","sample_list":"/paper/extending-context-window-of-large-language#ran","syntology_url":"https://syntology.ai/paper/2306.15595","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.15595"}},"official":null}},{"url":"/paper/summarunner-a-recurrent-neural-network-based","slug":"summarunner-a-recurrent-neural-network-based","title":"SummaRuNNer: A Recurrent Neural Network based Sequence Model for Extractive Summarization of Documents","date":"2016-11-14","arxiv_id":"1611.04230","repositories_listed":7,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"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","sample_list":"/paper/summarunner-a-recurrent-neural-network-based#ran","syntology_url":"https://syntology.ai/paper/1611.04230","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1611.04230"}},"official":null}},{"url":"/paper/bottom-up-abstractive-summarization","slug":"bottom-up-abstractive-summarization","title":"Bottom-Up Abstractive Summarization","date":"2018-08-31","arxiv_id":"1808.10792","repositories_listed":5,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":0,"n_instrument":5,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"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","sample_list":"/paper/bottom-up-abstractive-summarization#ran","syntology_url":"https://syntology.ai/paper/1808.10792","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1808.10792"}},"official":{"repos":["sebastianGehrmann/bottom-up-summary"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/generating-wikipedia-by-summarizing-long","slug":"generating-wikipedia-by-summarizing-long","title":"Generating Wikipedia by Summarizing Long Sequences","date":"2018-01-30","arxiv_id":"1801.10198","repositories_listed":4,"syntology":null},{"url":"/paper/primer-pyramid-based-masked-sentence-pre","slug":"primer-pyramid-based-masked-sentence-pre","title":"PRIMERA: Pyramid-based Masked Sentence Pre-training for Multi-document Summarization","date":"2021-10-16","arxiv_id":"2110.08499","repositories_listed":3,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":4,"n_instrument":3,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"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","sample_list":"/paper/primer-pyramid-based-masked-sentence-pre#ran","syntology_url":"https://syntology.ai/paper/2110.08499","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.08499"}},"official":{"repos":["allenai/primer"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/debatesum-a-large-scale-argument-mining-and","slug":"debatesum-a-large-scale-argument-mining-and","title":"DebateSum: A large-scale argument mining and summarization dataset","date":"2020-11-14","arxiv_id":"2011.07251","repositories_listed":3,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"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","sample_list":"/paper/debatesum-a-large-scale-argument-mining-and#ran","syntology_url":"https://syntology.ai/paper/2011.07251","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2011.07251"}},"official":{"repos":["Hellisotherpeople/DebateSum","Hellisotherpeople/debate2vec","arvind-balaji/debate-cards"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/aredsum-adaptive-redundancy-aware-iterative","slug":"aredsum-adaptive-redundancy-aware-iterative","title":"AREDSUM: Adaptive Redundancy-Aware Iterative Sentence Ranking for Extractive Document Summarization","date":"2020-04-13","arxiv_id":"2004.06176","repositories_listed":3,"syntology":null},{"url":"/paper/190600077","slug":"190600077","title":"Scoring Sentence Singletons and Pairs for Abstractive Summarization","date":"2019-05-31","arxiv_id":"1906.00077","repositories_listed":3,"syntology":null},{"url":"/paper/dont-give-me-the-details-just-the-summary","slug":"dont-give-me-the-details-just-the-summary","title":"Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarization","date":"2018-08-27","arxiv_id":"1808.08745","repositories_listed":3,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"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","sample_list":"/paper/dont-give-me-the-details-just-the-summary#ran","syntology_url":"https://syntology.ai/paper/1808.08745","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1808.08745"}},"official":{"repos":["shashiongithub/XSum"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/arctic-long-sequence-training-scalable-and","slug":"arctic-long-sequence-training-scalable-and","title":"Arctic Long Sequence Training: Scalable And Efficient Training For Multi-Million Token Sequences","date":"2025-06-16","arxiv_id":"2506.13996","repositories_listed":2,"syntology":null},{"url":"/paper/l-citeeval-do-long-context-models-truly","slug":"l-citeeval-do-long-context-models-truly","title":"L-CiteEval: Do Long-Context Models Truly Leverage Context for Responding?","date":"2024-10-03","arxiv_id":"2410.02115","repositories_listed":2,"syntology":null},{"url":"/paper/oarelatedwork-a-large-scale-dataset-of","slug":"oarelatedwork-a-large-scale-dataset-of","title":"OARelatedWork: A Large-Scale Dataset of Related Work Sections with Full-texts from Open Access Sources","date":"2024-05-03","arxiv_id":"2405.01930","repositories_listed":2,"syntology":null},{"url":"/paper/an-extractive-abstractive-approach-for-multi","slug":"an-extractive-abstractive-approach-for-multi","title":"An Extractive-Abstractive Approach for Multi-document Summarization of Scientific Articles for Literature Review","date":"2022-10-01","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/a-proposition-level-clustering-approach-for","slug":"a-proposition-level-clustering-approach-for","title":"Proposition-Level Clustering for Multi-Document Summarization","date":"2021-12-16","arxiv_id":"2112.08770","repositories_listed":2,"syntology":null},{"url":"/paper/summ-n-a-multi-stage-summarization-framework","slug":"summ-n-a-multi-stage-summarization-framework","title":"Summ^N: A Multi-Stage Summarization Framework for Long Input Dialogues and Documents","date":"2021-10-16","arxiv_id":"2110.10150","repositories_listed":2,"syntology":null},{"url":"/paper/ms2-multi-document-summarization-of-medical","slug":"ms2-multi-document-summarization-of-medical","title":"MS2: Multi-Document Summarization of Medical Studies","date":"2021-04-13","arxiv_id":"2104.06486","repositories_listed":2,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"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","sample_list":"/paper/ms2-multi-document-summarization-of-medical#ran","syntology_url":"https://syntology.ai/paper/2104.06486","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.06486"}},"official":{"repos":["allenai/ms2"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/quantitative-argument-summarization-and","slug":"quantitative-argument-summarization-and","title":"Quantitative Argument Summarization and Beyond: Cross-Domain Key Point Analysis","date":"2020-10-11","arxiv_id":"2010.05369","repositories_listed":2,"syntology":null},{"url":"/paper/attention-aware-inference-for-neural","slug":"attention-aware-inference-for-neural","title":"Global-aware Beam Search for Neural Abstractive Summarization","date":"2020-09-15","arxiv_id":"2009.06891","repositories_listed":2,"syntology":null},{"url":"/paper/generating-factual-narrative-summaries-of","slug":"generating-factual-narrative-summaries-of","title":"Generating (Factual?) Narrative Summaries of RCTs: Experiments with Neural Multi-Document Summarization","date":"2020-08-25","arxiv_id":"2008.11293","repositories_listed":2,"syntology":null},{"url":"/paper/pre-training-via-paraphrasing","slug":"pre-training-via-paraphrasing","title":"Pre-training via Paraphrasing","date":"2020-06-26","arxiv_id":"2006.15020","repositories_listed":2,"syntology":{"n":18,"n_ran":15,"n_constructed":0,"n_ran_checked":12,"n_instrument":3,"n_unverified":3,"n_honours":3,"n_violates":2,"n_no_contract":7,"n_pointer_only":3,"phrase":"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","sample_list":"/paper/pre-training-via-paraphrasing#ran","syntology_url":"https://syntology.ai/paper/2006.15020","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.15020"}},"official":null}},{"url":"/paper/leveraging-graph-to-improve-abstractive-multi","slug":"leveraging-graph-to-improve-abstractive-multi","title":"Leveraging Graph to Improve Abstractive Multi-Document Summarization","date":"2020-05-20","arxiv_id":"2005.10043","repositories_listed":2,"syntology":null},{"url":"/paper/on-faithfulness-and-factuality-in-abstractive","slug":"on-faithfulness-and-factuality-in-abstractive","title":"On Faithfulness and Factuality in Abstractive Summarization","date":"2020-05-02","arxiv_id":"2005.00661","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"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","sample_list":"/paper/on-faithfulness-and-factuality-in-abstractive#ran","syntology_url":"https://syntology.ai/paper/2005.00661","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.00661"}},"official":{"repos":["google-research-datasets/xsum_hallucination_annotations"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["found_in_text"]}}},{"url":"/paper/screenplay-summarization-using-latent","slug":"screenplay-summarization-using-latent","title":"Screenplay Summarization Using Latent Narrative Structure","date":"2020-04-27","arxiv_id":"2004.12727","repositories_listed":2,"syntology":null},{"url":"/paper/extractive-summarization-as-text-matching","slug":"extractive-summarization-as-text-matching","title":"Extractive Summarization as Text Matching","date":"2020-04-19","arxiv_id":"2004.08795","repositories_listed":2,"syntology":null},{"url":"/paper/tf-ranking-scalable-tensorflow-library-for","slug":"tf-ranking-scalable-tensorflow-library-for","title":"TF-Ranking: Scalable TensorFlow Library for Learning-to-Rank","date":"2018-11-30","arxiv_id":"1812.00073","repositories_listed":2,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"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","sample_list":"/paper/tf-ranking-scalable-tensorflow-library-for#ran","syntology_url":"https://syntology.ai/paper/1812.00073","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1812.00073"}},"official":{"repos":["tensorflow/ranking"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/tap-dlnd-10-a-corpus-for-document-level","slug":"tap-dlnd-10-a-corpus-for-document-level","title":"TAP-DLND 1.0 : A Corpus for Document Level Novelty Detection","date":"2018-02-20","arxiv_id":"1802.06950","repositories_listed":2,"syntology":null},{"url":"/paper/neural-extractive-summarization-with-side","slug":"neural-extractive-summarization-with-side","title":"Neural Extractive Summarization with Side Information","date":"2017-04-14","arxiv_id":"1704.04530","repositories_listed":2,"syntology":null},{"url":"/paper/centroid-based-text-summarization-through","slug":"centroid-based-text-summarization-through","title":"Centroid-based Text Summarization through Compositionality of Word Embeddings","date":"2017-04-01","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/generationprograms-fine-grained-attribution","slug":"generationprograms-fine-grained-attribution","title":"GenerationPrograms: Fine-grained Attribution with Executable Programs","date":"2025-06-17","arxiv_id":"2506.14580","repositories_listed":1,"syntology":null},{"url":"/paper/improving-fairness-of-large-language-models","slug":"improving-fairness-of-large-language-models","title":"Improving Fairness of Large Language Models in Multi-document Summarization","date":"2025-06-09","arxiv_id":"2506.07479","repositories_listed":1,"syntology":null},{"url":"/paper/ask-retrieve-summarize-a-modular-pipeline-for","slug":"ask-retrieve-summarize-a-modular-pipeline-for","title":"Ask, Retrieve, Summarize: A Modular Pipeline for Scientific Literature Summarization","date":"2025-05-22","arxiv_id":"2505.16349","repositories_listed":1,"syntology":null},{"url":"/paper/estimating-optimal-context-length-for-hybrid","slug":"estimating-optimal-context-length-for-hybrid","title":"Estimating Optimal Context Length for Hybrid Retrieval-augmented Multi-document Summarization","date":"2025-04-17","arxiv_id":"2504.12972","repositories_listed":1,"syntology":null},{"url":"/paper/unihdsa-a-unified-relation-prediction","slug":"unihdsa-a-unified-relation-prediction","title":"UniHDSA: A Unified Relation Prediction Approach for Hierarchical Document Structure Analysis","date":"2025-03-20","arxiv_id":"2503.15893","repositories_listed":1,"syntology":null},{"url":"/paper/agent-enhanced-large-language-models-for","slug":"agent-enhanced-large-language-models-for","title":"Agent-Enhanced Large Language Models for Researching Political Institutions","date":"2025-03-14","arxiv_id":"2503.13524","repositories_listed":1,"syntology":null},{"url":"/paper/scaling-multi-document-event-summarization","slug":"scaling-multi-document-event-summarization","title":"Scaling Multi-Document Event Summarization: Evaluating Compression vs. Full-Text Approaches","date":"2025-02-10","arxiv_id":"2502.06617","repositories_listed":1,"syntology":null},{"url":"/paper/coverage-based-fairness-in-multi-document","slug":"coverage-based-fairness-in-multi-document","title":"Coverage-based Fairness in Multi-document Summarization","date":"2024-12-11","arxiv_id":"2412.08795","repositories_listed":1,"syntology":null},{"url":"/paper/fair-summarization-bridging-quality-and","slug":"fair-summarization-bridging-quality-and","title":"Fair Summarization: Bridging Quality and Diversity in Extractive Summaries","date":"2024-11-12","arxiv_id":"2411.07521","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":5,"phrase":"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","sample_list":"/paper/fair-summarization-bridging-quality-and#ran","syntology_url":"https://syntology.ai/paper/2411.07521","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.07521"}},"official":{"repos":["PortNLP/FairEXTSummarizer"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/what-is-wrong-with-perplexity-for-long","slug":"what-is-wrong-with-perplexity-for-long","title":"What is Wrong with Perplexity for Long-context Language Modeling?","date":"2024-10-31","arxiv_id":"2410.23771","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"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","sample_list":"/paper/what-is-wrong-with-perplexity-for-long#ran","syntology_url":"https://syntology.ai/paper/2410.23771","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.23771"}},"official":{"repos":["pku-ml/longppl"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/from-single-to-multi-how-llms-hallucinate-in","slug":"from-single-to-multi-how-llms-hallucinate-in","title":"From Single to Multi: How LLMs Hallucinate in Multi-Document Summarization","date":"2024-10-17","arxiv_id":"2410.13961","repositories_listed":1,"syntology":null},{"url":"/paper/globesumm-a-challenging-benchmark-towards","slug":"globesumm-a-challenging-benchmark-towards","title":"GlobeSumm: A Challenging Benchmark Towards Unifying Multi-lingual, Cross-lingual and Multi-document News Summarization","date":"2024-10-05","arxiv_id":"2410.04087","repositories_listed":1,"syntology":null},{"url":"/paper/preference-guided-reflective-sampling-for","slug":"preference-guided-reflective-sampling-for","title":"Preference-Guided Reflective Sampling for Aligning Language Models","date":"2024-08-22","arxiv_id":"2408.12163","repositories_listed":1,"syntology":null},{"url":"/paper/glimmer-incorporating-graph-and-lexical","slug":"glimmer-incorporating-graph-and-lexical","title":"GLIMMER: Incorporating Graph and Lexical Features in Unsupervised Multi-Document Summarization","date":"2024-08-19","arxiv_id":"2408.10115","repositories_listed":1,"syntology":null},{"url":"/paper/moviesum-an-abstractive-summarization-dataset","slug":"moviesum-an-abstractive-summarization-dataset","title":"MovieSum: An Abstractive Summarization Dataset for Movie Screenplays","date":"2024-08-12","arxiv_id":"2408.06281","repositories_listed":1,"syntology":null},{"url":"/paper/ideal-leveraging-infinite-and-dynamic","slug":"ideal-leveraging-infinite-and-dynamic","title":"IDEAL: Leveraging Infinite and Dynamic Characterizations of Large Language Models for Query-focused Summarization","date":"2024-07-15","arxiv_id":"2407.10486","repositories_listed":1,"syntology":null},{"url":"/paper/glimpse-pragmatically-informative-multi","slug":"glimpse-pragmatically-informative-multi","title":"GLIMPSE: Pragmatically Informative Multi-Document Summarization for Scholarly Reviews","date":"2024-06-11","arxiv_id":"2406.07359","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/glimpse-pragmatically-informative-multi#ran","syntology_url":"https://syntology.ai/paper/2406.07359","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.07359"}},"official":{"repos":["icannos/glimpse-mds"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/checkembed-effective-verification-of-llm","slug":"checkembed-effective-verification-of-llm","title":"CheckEmbed: Effective Verification of LLM Solutions to Open-Ended Tasks","date":"2024-06-04","arxiv_id":"2406.02524","repositories_listed":1,"syntology":null},{"url":"/paper/the-power-of-summary-source-alignments","slug":"the-power-of-summary-source-alignments","title":"The Power of Summary-Source Alignments","date":"2024-06-02","arxiv_id":"2406.00842","repositories_listed":1,"syntology":null},{"url":"/paper/text-generation-a-systematic-literature","slug":"text-generation-a-systematic-literature","title":"Text Generation: A Systematic Literature Review of Tasks, Evaluation, and Challenges","date":"2024-05-24","arxiv_id":"2405.15604","repositories_listed":1,"syntology":null},{"url":"/paper/which-information-matters-dissecting-human","slug":"which-information-matters-dissecting-human","title":"Which Information Matters? Dissecting Human-written Multi-document Summaries with Partial Information Decomposition","date":"2024-05-23","arxiv_id":"2405.14470","repositories_listed":1,"syntology":null},{"url":"/paper/hierarchical-attention-graph-for-scientific","slug":"hierarchical-attention-graph-for-scientific","title":"Hierarchical Attention Graph for Scientific Document Summarization in Global and Local Level","date":"2024-05-16","arxiv_id":"2405.10202","repositories_listed":1,"syntology":null},{"url":"/paper/disentangling-specificity-for-abstractive","slug":"disentangling-specificity-for-abstractive","title":"Disentangling Specificity for Abstractive Multi-document Summarization","date":"2024-05-12","arxiv_id":"2406.00005","repositories_listed":1,"syntology":null},{"url":"/paper/large-language-models-in-healthcare-a","slug":"large-language-models-in-healthcare-a","title":"Large Language Models in the Clinic: A Comprehensive Benchmark","date":"2024-04-25","arxiv_id":"2405.00716","repositories_listed":1,"syntology":null},{"url":"/paper/multi-news-cost-efficient-dataset-cleansing","slug":"multi-news-cost-efficient-dataset-cleansing","title":"Multi-News+: Cost-efficient Dataset Cleansing via LLM-based Data Annotation","date":"2024-04-15","arxiv_id":"2404.09682","repositories_listed":1,"syntology":null},{"url":"/paper/attribute-first-then-generate-locally","slug":"attribute-first-then-generate-locally","title":"Attribute First, then Generate: Locally-attributable Grounded Text Generation","date":"2024-03-25","arxiv_id":"2403.17104","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"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","sample_list":"/paper/attribute-first-then-generate-locally#ran","syntology_url":"https://syntology.ai/paper/2403.17104","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.17104"}},"official":{"repos":["lovodkin93/attribute-first-then-generate"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/investigating-text-shortening-strategy-in","slug":"investigating-text-shortening-strategy-in","title":"Investigating Text Shortening Strategy in BERT: Truncation vs Summarization","date":"2024-03-19","arxiv_id":"2403.12799","repositories_listed":1,"syntology":null},{"url":"/paper/detect-order-construct-a-tree-construction","slug":"detect-order-construct-a-tree-construction","title":"Detect-Order-Construct: A Tree Construction based Approach for Hierarchical Document Structure Analysis","date":"2024-01-22","arxiv_id":"2401.11874","repositories_listed":1,"syntology":null},{"url":"/paper/shaping-political-discourse-using-multi","slug":"shaping-political-discourse-using-multi","title":"Shaping Political Discourse using multi-source News Summarization","date":"2023-12-18","arxiv_id":"2312.11703","repositories_listed":1,"syntology":null},{"url":"/paper/openasp-a-benchmark-for-multi-document-open","slug":"openasp-a-benchmark-for-multi-document-open","title":"OpenAsp: A Benchmark for Multi-document Open Aspect-based Summarization","date":"2023-12-07","arxiv_id":"2312.04440","repositories_listed":1,"syntology":null},{"url":"/paper/supervising-the-centroid-baseline-for","slug":"supervising-the-centroid-baseline-for","title":"Supervising the Centroid Baseline for Extractive Multi-Document Summarization","date":"2023-11-29","arxiv_id":"2311.17771","repositories_listed":1,"syntology":null},{"url":"/paper/pelms-pre-training-for-effective-low-shot","slug":"pelms-pre-training-for-effective-low-shot","title":"PELMS: Pre-training for Effective Low-Shot Multi-Document Summarization","date":"2023-11-16","arxiv_id":"2311.09836","repositories_listed":1,"syntology":null},{"url":"/paper/non-parametric-memory-guidance-for-multi","slug":"non-parametric-memory-guidance-for-multi","title":"Non-Parametric Memory Guidance for Multi-Document Summarization","date":"2023-11-14","arxiv_id":"2311.10760","repositories_listed":1,"syntology":null},{"url":"/paper/embrace-divergence-for-richer-insights-a","slug":"embrace-divergence-for-richer-insights-a","title":"Embrace Divergence for Richer Insights: A Multi-document Summarization Benchmark and a Case Study on Summarizing Diverse Information from News Articles","date":"2023-09-17","arxiv_id":"2309.09369","repositories_listed":1,"syntology":null},{"url":"/paper/odsum-new-benchmarks-for-open-domain-multi","slug":"odsum-new-benchmarks-for-open-domain-multi","title":"ODSum: New Benchmarks for Open Domain Multi-Document Summarization","date":"2023-09-16","arxiv_id":"2309.08960","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"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","sample_list":"/paper/odsum-new-benchmarks-for-open-domain-multi#ran","syntology_url":"https://syntology.ai/paper/2309.08960","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.08960"}},"official":{"repos":["yale-nlp/odsum"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/investigating-gender-bias-in-news","slug":"investigating-gender-bias-in-news","title":"Bias in News Summarization: Measures, Pitfalls and Corpora","date":"2023-09-14","arxiv_id":"2309.08047","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"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","sample_list":"/paper/investigating-gender-bias-in-news#ran","syntology_url":"https://syntology.ai/paper/2309.08047","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.08047"}},"official":{"repos":["julmaxi/summary_bias"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/pre-training-meets-clustering-a-hybrid","slug":"pre-training-meets-clustering-a-hybrid","title":"Pre-training Meets Clustering: A Hybrid Extractive Multi-document Summarization Model","date":"2023-05-25","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/fourier-transformer-fast-long-range-modeling","slug":"fourier-transformer-fast-long-range-modeling","title":"Fourier Transformer: Fast Long Range Modeling by Removing Sequence Redundancy with FFT Operator","date":"2023-05-24","arxiv_id":"2305.15099","repositories_listed":1,"syntology":null},{"url":"/paper/revisiting-sentence-union-generation-as-a","slug":"revisiting-sentence-union-generation-as-a","title":"Revisiting Sentence Union Generation as a Testbed for Text Consolidation","date":"2023-05-24","arxiv_id":"2305.15605","repositories_listed":1,"syntology":null},{"url":"/paper/automated-metrics-for-medical-multi-document","slug":"automated-metrics-for-medical-multi-document","title":"Automated Metrics for Medical Multi-Document Summarization Disagree with Human Evaluations","date":"2023-05-23","arxiv_id":"2305.13693","repositories_listed":1,"syntology":null},{"url":"/paper/a-hierarchical-encoding-decoding-scheme-for","slug":"a-hierarchical-encoding-decoding-scheme-for","title":"A Hierarchical Encoding-Decoding Scheme for Abstractive Multi-document Summarization","date":"2023-05-15","arxiv_id":"2305.08503","repositories_listed":1,"syntology":null},{"url":"/paper/towards-summarizing-multiple-documents-with","slug":"towards-summarizing-multiple-documents-with","title":"Summarizing Multiple Documents with Conversational Structure for Meta-Review Generation","date":"2023-05-02","arxiv_id":"2305.01498","repositories_listed":1,"syntology":null},{"url":"/paper/unleashing-infinite-length-input-capacity-for","slug":"unleashing-infinite-length-input-capacity-for","title":"Enhancing Large Language Model with Self-Controlled Memory Framework","date":"2023-04-26","arxiv_id":"2304.13343","repositories_listed":1,"syntology":{"n":14,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":11,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"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","sample_list":"/paper/unleashing-infinite-length-input-capacity-for#ran","syntology_url":"https://syntology.ai/paper/2304.13343","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.13343"}},"official":{"repos":["wbbeyourself/scm4llms"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":11,"ran_from_kinds":["official"]}}},{"url":"/paper/xwikigen-cross-lingual-summarization-for","slug":"xwikigen-cross-lingual-summarization-for","title":"XWikiGen: Cross-lingual Summarization for Encyclopedic Text Generation in Low Resource Languages","date":"2023-03-22","arxiv_id":"2303.12308","repositories_listed":1,"syntology":null},{"url":"/paper/compressed-heterogeneous-graph-for","slug":"compressed-heterogeneous-graph-for","title":"Compressed Heterogeneous Graph for Abstractive Multi-Document Summarization","date":"2023-03-12","arxiv_id":"2303.06565","repositories_listed":1,"syntology":null},{"url":"/paper/pdsum-prototype-driven-continuous","slug":"pdsum-prototype-driven-continuous","title":"PDSum: Prototype-driven Continuous Summarization of Evolving Multi-document Sets Stream","date":"2023-02-10","arxiv_id":"2302.05550","repositories_listed":1,"syntology":null},{"url":"/paper/generating-a-structured-summary-of-numerous","slug":"generating-a-structured-summary-of-numerous","title":"Generating a Structured Summary of Numerous Academic Papers: Dataset and Method","date":"2023-02-09","arxiv_id":"2302.04580","repositories_listed":1,"syntology":null},{"url":"/paper/long-text-and-multi-table-summarization","slug":"long-text-and-multi-table-summarization","title":"Long Text and Multi-Table Summarization: Dataset and Method","date":"2023-02-08","arxiv_id":"2302.03815","repositories_listed":1,"syntology":null},{"url":"/paper/follow-the-timeline-generating-abstractive","slug":"follow-the-timeline-generating-abstractive","title":"Follow the Timeline! Generating Abstractive and Extractive Timeline Summary in Chronological Order","date":"2023-01-02","arxiv_id":"2301.00867","repositories_listed":1,"syntology":null},{"url":"/paper/gae-isumm-unsupervised-graph-based","slug":"gae-isumm-unsupervised-graph-based","title":"GAE-ISumm: Unsupervised Graph-Based Summarization of Indian Languages","date":"2022-12-25","arxiv_id":"2212.12937","repositories_listed":1,"syntology":null},{"url":"/paper/sumren-summarizing-reported-speech-about","slug":"sumren-summarizing-reported-speech-about","title":"SumREN: Summarizing Reported Speech about Events in News","date":"2022-12-02","arxiv_id":"2212.01146","repositories_listed":1,"syntology":null},{"url":"/paper/gosum-extractive-summarization-of-long","slug":"gosum-extractive-summarization-of-long","title":"GoSum: Extractive Summarization of Long Documents by Reinforcement Learning and Graph Organized discourse state","date":"2022-11-18","arxiv_id":"2211.10247","repositories_listed":1,"syntology":null},{"url":"/paper/evaluating-and-improving-factuality-in","slug":"evaluating-and-improving-factuality-in","title":"Evaluating and Improving Factuality in Multimodal Abstractive Summarization","date":"2022-11-04","arxiv_id":"2211.02580","repositories_listed":1,"syntology":null},{"url":"/paper/toward-unifying-text-segmentation-and-long","slug":"toward-unifying-text-segmentation-and-long","title":"Toward Unifying Text Segmentation and Long Document Summarization","date":"2022-10-28","arxiv_id":"2210.16422","repositories_listed":1,"syntology":null},{"url":"/paper/universal-evasion-attacks-on-summarization","slug":"universal-evasion-attacks-on-summarization","title":"Universal Evasion Attacks on Summarization Scoring","date":"2022-10-25","arxiv_id":"2210.14260","repositories_listed":1,"syntology":null},{"url":"/paper/how-multi-is-multi-document-summarization","slug":"how-multi-is-multi-document-summarization","title":"How \"Multi\" is Multi-Document Summarization?","date":"2022-10-23","arxiv_id":"2210.12688","repositories_listed":1,"syntology":null},{"url":"/paper/legal-case-document-summarization-extractive","slug":"legal-case-document-summarization-extractive","title":"Legal Case Document Summarization: Extractive and Abstractive Methods and their Evaluation","date":"2022-10-14","arxiv_id":"2210.07544","repositories_listed":1,"syntology":null},{"url":"/paper/hegel-hypergraph-transformer-for-long","slug":"hegel-hypergraph-transformer-for-long","title":"HEGEL: Hypergraph Transformer for Long Document Summarization","date":"2022-10-09","arxiv_id":"2210.04126","repositories_listed":1,"syntology":null},{"url":"/paper/gusum-graph-based-unsupervised-summarization-1","slug":"gusum-graph-based-unsupervised-summarization-1","title":"GUSUM: Graph-based Unsupervised Summarization Using Sentence Features Scoring and Sentence-BERT","date":"2022-10-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/ltrc-mup-2022-multi-perspective-scientific","slug":"ltrc-mup-2022-multi-perspective-scientific","title":"LTRC @MuP 2022: Multi-Perspective Scientific Document Summarization Using Pre-trained Generation Models","date":"2022-10-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/multi-graph-neural-network-for-extractive","slug":"multi-graph-neural-network-for-extractive","title":"Multi Graph Neural Network for Extractive Long Document Summarization","date":"2022-10-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/overview-of-mslr2022-a-shared-task-on-multi","slug":"overview-of-mslr2022-a-shared-task-on-multi","title":"Overview of MSLR2022: A Shared Task on Multi-document Summarization for Literature Reviews","date":"2022-10-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/overview-of-the-first-shared-task-on-multi","slug":"overview-of-the-first-shared-task-on-multi","title":"Overview of the First Shared Task on Multi Perspective Scientific Document Summarization (MuP)","date":"2022-10-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/uper-boosting-multi-document-summarization","slug":"uper-boosting-multi-document-summarization","title":"UPER: Boosting Multi-Document Summarization with an Unsupervised Prompt-based Extractor","date":"2022-10-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/an-efficient-coarse-to-fine-facet-aware","slug":"an-efficient-coarse-to-fine-facet-aware","title":"An Efficient Coarse-to-Fine Facet-Aware Unsupervised Summarization Framework based on Semantic Blocks","date":"2022-08-17","arxiv_id":"2208.08253","repositories_listed":1,"syntology":null},{"url":"/paper/multi-document-summarization-with-centroid","slug":"multi-document-summarization-with-centroid","title":"Multi-Document Summarization with Centroid-Based Pretraining","date":"2022-08-01","arxiv_id":"2208.01006","repositories_listed":1,"syntology":null},{"url":"/paper/an-empirical-survey-on-long-document","slug":"an-empirical-survey-on-long-document","title":"An Empirical Survey on Long Document Summarization: Datasets, Models and Metrics","date":"2022-07-03","arxiv_id":"2207.00939","repositories_listed":1,"syntology":null}],"syntology_records":20,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":4,"papers_placed":0,"judged_by":{"model":"Claude Sonnet 4.5","models_as_recorded":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[{"leaderboard":"/sota/document-summarization-on-cnn-daily-mail","since_archive":"/sota/document-summarization-on-cnn-daily-mail#since-judged","papers_judged":4,"placed":0}]},"papers_where_code_ran":34,"papers_where_code_ran_first_page":"/task/document-summarization/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"archive","page":2,"of":8,"url":"/task/document-summarization/papers/2","json":"/task/document-summarization/papers/2.json","rows":100},{"order":"archive","page":3,"of":8,"url":"/task/document-summarization/papers/3","json":"/task/document-summarization/papers/3.json","rows":100},{"order":"archive","page":4,"of":8,"url":"/task/document-summarization/papers/4","json":"/task/document-summarization/papers/4.json","rows":100},{"order":"archive","page":5,"of":8,"url":"/task/document-summarization/papers/5","json":"/task/document-summarization/papers/5.json","rows":100},{"order":"archive","page":6,"of":8,"url":"/task/document-summarization/papers/6","json":"/task/document-summarization/papers/6.json","rows":100},{"order":"archive","page":7,"of":8,"url":"/task/document-summarization/papers/7","json":"/task/document-summarization/papers/7.json","rows":100},{"order":"archive","page":8,"of":8,"url":"/task/document-summarization/papers/8","json":"/task/document-summarization/papers/8.json","rows":60},{"order":"ran","page":1,"of":1,"url":"/task/document-summarization/papers/ran/1","json":"/task/document-summarization/papers/ran/1.json","rows":34}],"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"8b4554dc8e012e597b89d87f018a37180dedb570ecd25506689b30c9e615437c","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}