{"url":"/task/cross-document-language-modeling","name":"Cross-Document Language Modeling","slug":"cross-document-language-modeling","description_markdown":"Involves pretraining language models to support multi-document NLP tasks.\r\n\r\nSource: [Cross-Document Language Modeling](https://arxiv.org/pdf/2101.00406v1.pdf)\r\n\r\nImage Credit: [Cross-Document Language Modeling](https://arxiv.org/pdf/2101.00406v1.pdf)","categories":[{"name":"Medical","url":"/area/medical"},{"name":"Miscellaneous","url":"/area/miscellaneous"},{"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":1,"papers_with_code":1,"benchmarks":2,"benchmark_tables_in_archive":2,"benchmark_tables_shown":2,"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":1,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/cross-document-language-modeling-on-multinews","slug":"cross-document-language-modeling-on-multinews","dataset":"MultiNews val","dataset_url":"/dataset/multi-news","rows_in_archive":3,"metrics":["Perplexity"],"first_row_in_archive_order":{"model":"CD-LM","paper_title":"CDLM: Cross-Document Language Modeling","paper_url":"/paper/cross-document-language-modeling","paper_date":"2021-01-02","arxiv_id":"2101.00406","code_links":[{"title":"aviclu/cdlm","url":"https://github.com/aviclu/cdlm"},{"title":"aviclu/CD-LM","url":"https://github.com/aviclu/CD-LM"}],"syntology":null}},{"leaderboard":"/sota/cross-document-language-modeling-on-multinews-1","slug":"cross-document-language-modeling-on-multinews-1","dataset":"MultiNews test","dataset_url":"/dataset/multi-news","rows_in_archive":3,"metrics":["Perplexity"],"first_row_in_archive_order":{"model":"CD-LM","paper_title":"CDLM: Cross-Document Language Modeling","paper_url":"/paper/cross-document-language-modeling","paper_date":"2021-01-02","arxiv_id":"2101.00406","code_links":[{"title":"aviclu/cdlm","url":"https://github.com/aviclu/cdlm"},{"title":"aviclu/CD-LM","url":"https://github.com/aviclu/CD-LM"}],"syntology":null}}],"datasets":[{"url":"/dataset/multi-news","name":"Multi-News","full_name":"Multi-News","num_papers_in_archive":122}],"subtasks":[],"parent_tasks":[{"url":"/task/language-modelling","name":"Language Modelling"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":1,"of":1,"tagged_in_all":1,"items":[{"url":"/paper/cross-document-language-modeling","title":"CDLM: Cross-Document Language Modeling","date":"2021-01-02","arxiv_id":"2101.00406","repositories_listed":2,"syntology":null}],"syntology_records":0,"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"},"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":"2026-09-24T18:15:14+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; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"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"}}