{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/madlad-400-a-multilingual-and-document-level","title":"MADLAD-400: A Multilingual And Document-Level Large Audited Dataset","arxiv_id":"2309.04662","date":"2023-09-09","proceeding":"NeurIPS 2023 11","authors":[],"abstract":"We introduce MADLAD-400, a manually audited, general domain 3T token monolingual dataset based on CommonCrawl, spanning 419 languages. We discuss the limitations revealed by self-auditing MADLAD-400, and the role data auditing had in the dataset creation process. We then train and release a 10.7B-parameter multilingual machine translation model on 250 billion tokens covering over 450 languages using publicly available data, and find that it is competitive with models that are significantly larger, and report the results on different domains. In addition, we train a 8B-parameter language model, and assess the results on few-shot translation. We make the baseline models available to the research community.","url_abs":"https://arxiv.org/abs/2309.04662v1","url_pdf":"https://arxiv.org/pdf/2309.04662v1.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":"madlad-400-a-multilingual-and-document-level","repo_url":"https://github.com/bramiozo/PubScience","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"translation","task_name":"Translation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2309.04662","atlas_url":"https://app.syntology.ai/?focus=2309.04662","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.04662"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/bramiozo/PubScience","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":7},"by_repo_kind":{"listed":{"samples":7,"ran":7,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"7af1598325b4e1cc","entry":"SeinenCorpusPrep","repo":"bramiozo/PubScience","repo_kind":"listed","path":"src/pubscience/parse/pubtator.py","file_url":"https://github.com/bramiozo/PubScience/blob/HEAD/src/pubscience/parse/pubtator.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7af1598325b4e1cc"}},{"code_sha256_prefix":"04acf69863589dc8","entry":"add_semantic_types","repo":"bramiozo/PubScience","repo_kind":"listed","path":"src/pubscience/parse/pubtator.py","file_url":"https://github.com/bramiozo/PubScience/blob/HEAD/src/pubscience/parse/pubtator.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"04acf69863589dc8"}},{"code_sha256_prefix":"849de0c8feb5a9d5","entry":"compute_entropy","repo":"bramiozo/PubScience","repo_kind":"listed","path":"src/pubscience/clean/cleaner.py","file_url":"https://github.com/bramiozo/PubScience/blob/HEAD/src/pubscience/clean/cleaner.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"849de0c8feb5a9d5"}},{"code_sha256_prefix":"a1b35978ea402c8c","entry":"ensure_directory","repo":"bramiozo/PubScience","repo_kind":"listed","path":"src/pubscience/retrieve/retrieve_atc.py","file_url":"https://github.com/bramiozo/PubScience/blob/HEAD/src/pubscience/retrieve/retrieve_atc.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a1b35978ea402c8c"}},{"code_sha256_prefix":"8b12b005cb939e5b","entry":"get_char_entr","repo":"bramiozo/PubScience","repo_kind":"listed","path":"src/pubscience/clean/cleaner.py","file_url":"https://github.com/bramiozo/PubScience/blob/HEAD/src/pubscience/clean/cleaner.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8b12b005cb939e5b"}},{"code_sha256_prefix":"698b8f9d59280f86","entry":"get_char_seq","repo":"bramiozo/PubScience","repo_kind":"listed","path":"src/pubscience/clean/cleaner.py","file_url":"https://github.com/bramiozo/PubScience/blob/HEAD/src/pubscience/clean/cleaner.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"698b8f9d59280f86"}},{"code_sha256_prefix":"9154f133c506c97c","entry":"is_valid_atc_code","repo":"bramiozo/PubScience","repo_kind":"listed","path":"src/pubscience/retrieve/retrieve_atc.py","file_url":"https://github.com/bramiozo/PubScience/blob/HEAD/src/pubscience/retrieve/retrieve_atc.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"9154f133c506c97c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}