{"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":"/paper/cross-document-language-modeling","title":"CDLM: Cross-Document Language Modeling","arxiv_id":"2101.00406","date":"2021-01-02","proceeding":"Findings (EMNLP) 2021 11","authors":["Avi Caciularu","Arman Cohan","Iz Beltagy","Matthew E. Peters","Arie Cattan","Ido Dagan"],"abstract":"We introduce a new pretraining approach geared for multi-document language modeling, incorporating two key ideas into the masked language modeling self-supervised objective. First, instead of considering documents in isolation, we pretrain over sets of multiple related documents, encouraging the model to learn cross-document relationships. Second, we improve over recent long-range transformers by introducing dynamic global attention that has access to the entire input to predict masked tokens. We release CDLM (Cross-Document Language Model), a new general language model for multi-document setting that can be easily applied to downstream tasks. Our extensive analysis shows that both ideas are essential for the success of CDLM, and work in synergy to set new state-of-the-art results for several multi-text tasks. Code and models are available at https://github.com/aviclu/CDLM.","url_abs":"https://arxiv.org/abs/2101.00406v2","url_pdf":"https://arxiv.org/pdf/2101.00406v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"cross-document-language-modeling","repo_url":"https://github.com/aviclu/CD-LM","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"cross-document-language-modeling","repo_url":"https://github.com/aviclu/cdlm","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"citation-recommendation","task_name":"Citation Recommendation"},{"task_slug":"coreference-resolution","task_name":"Coreference Resolution"},{"task_slug":"cross-document-language-modeling","task_name":"Cross-Document Language Modeling"},{"task_slug":"entity-cross-document-coreference-resolution","task_name":"Entity Cross-Document Coreference Resolution"},{"task_slug":"event-coreference-resolution","task_name":"Event Coreference Resolution"},{"task_slug":"event-cross-document-coreference-resolution","task_name":"Event Cross-Document Coreference Resolution"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"masked-language-modeling","task_name":"Masked Language Modeling"},{"task_slug":"question-answering","task_name":"Question Answering"}],"methods":[{"method_slug":"adamw","method_name":"AdamW"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-linear-decay","method_name":"Linear Warmup With Linear Decay"},{"method_slug":"longformer","method_name":"Longformer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"weight-decay","method_name":"Weight Decay"},{"method_slug":"wordpiece","method_name":"WordPiece"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/cross-document-language-modeling-on-multinews-1","task":"Cross-Document Language Modeling","dataset":"MultiNews test","model":"CD-LM","rank_in_archive_order":1,"of":3,"metrics":{"Perplexity":"1.76"},"uses_additional_data":false},{"leaderboard":"/sota/cross-document-language-modeling-on-multinews-1","task":"Cross-Document Language Modeling","dataset":"MultiNews test","model":"Rand CD-LM","rank_in_archive_order":2,"of":3,"metrics":{"Perplexity":"1.93"},"uses_additional_data":false},{"leaderboard":"/sota/cross-document-language-modeling-on-multinews-1","task":"Cross-Document Language Modeling","dataset":"MultiNews test","model":"Longformer","rank_in_archive_order":3,"of":3,"metrics":{"Perplexity":"2.34"},"uses_additional_data":false},{"leaderboard":"/sota/cross-document-language-modeling-on-multinews","task":"Cross-Document Language Modeling","dataset":"MultiNews val","model":"CD-LM","rank_in_archive_order":1,"of":3,"metrics":{"Perplexity":"1.69"},"uses_additional_data":false},{"leaderboard":"/sota/cross-document-language-modeling-on-multinews","task":"Cross-Document Language Modeling","dataset":"MultiNews val","model":"Rand CD-LM","rank_in_archive_order":2,"of":3,"metrics":{"Perplexity":"1.88"},"uses_additional_data":false},{"leaderboard":"/sota/cross-document-language-modeling-on-multinews","task":"Cross-Document Language Modeling","dataset":"MultiNews val","model":"Longformer","rank_in_archive_order":3,"of":3,"metrics":{"Perplexity":"2.03"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2101.00406","atlas_url":"https://app.syntology.ai/?focus=2101.00406","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2101.00406"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2101.00406\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2101.00406"},"call":"get_concepts_for_paper(arxiv_id=\"2101.00406\")"}],"by_repo":[{"repo":"aviclu/CD-LM","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"aviclu/cdlm","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"f5224f373050fd3bde21e56489cb09cd47ae5385c8f9e53c2da1e0c344878065","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}