{"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/multiblimp-1-0-a-massively-multilingual","title":"MultiBLiMP 1.0: A Massively Multilingual Benchmark of Linguistic Minimal Pairs","arxiv_id":"2504.02768","date":"2025-04-03","proceeding":null,"authors":["Jaap Jumelet","Leonie Weissweiler","Arianna Bisazza"],"abstract":"We introduce MultiBLiMP 1.0, a massively multilingual benchmark of linguistic minimal pairs, covering 101 languages, 6 linguistic phenomena and containing more than 125,000 minimal pairs. Our minimal pairs are created using a fully automated pipeline, leveraging the large-scale linguistic resources of Universal Dependencies and UniMorph. MultiBLiMP 1.0 evaluates abilities of LLMs at an unprecedented multilingual scale, and highlights the shortcomings of the current state-of-the-art in modelling low-resource languages.","url_abs":"https://arxiv.org/abs/2504.02768v1","url_pdf":"https://arxiv.org/pdf/2504.02768v1.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":"multiblimp-1-0-a-massively-multilingual","repo_url":"https://github.com/jumelet/multiblimp","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2504.02768","atlas_url":"https://app.syntology.ai/?focus=2504.02768","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.02768"}},"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/jumelet/multiblimp","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":7,"unverified":6},"by_repo_kind":{"official":{"samples":13,"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":"69515b6abc0fa47f","entry":"allval2um","repo":"jumelet/multiblimp","repo_kind":"official","path":"src/multiblimp/unimorph.py","file_url":"https://github.com/jumelet/multiblimp/blob/HEAD/src/multiblimp/unimorph.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":"69515b6abc0fa47f"}},{"code_sha256_prefix":"63a16b3890a00995","entry":"get_ud_langs","repo":"jumelet/multiblimp","repo_kind":"official","path":"src/multiblimp/languages.py","file_url":"https://github.com/jumelet/multiblimp/blob/HEAD/src/multiblimp/languages.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":"63a16b3890a00995"}},{"code_sha256_prefix":"1212c3a5ab7a94a1","entry":"has_typo","repo":"jumelet/multiblimp","repo_kind":"official","path":"src/multiblimp/treebank.py","file_url":"https://github.com/jumelet/multiblimp/blob/HEAD/src/multiblimp/treebank.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":"1212c3a5ab7a94a1"}},{"code_sha256_prefix":"88ac677b8941041f","entry":"is_finite","repo":"jumelet/multiblimp","repo_kind":"official","path":"src/multiblimp/ud2um.py","file_url":"https://github.com/jumelet/multiblimp/blob/HEAD/src/multiblimp/ud2um.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":"88ac677b8941041f"}},{"code_sha256_prefix":"ec0ad2d9f0e52dc3","entry":"latin_to_cyrillic","repo":"jumelet/multiblimp","repo_kind":"official","path":"src/multiblimp/languages.py","file_url":"https://github.com/jumelet/multiblimp/blob/HEAD/src/multiblimp/languages.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":"ec0ad2d9f0e52dc3"}},{"code_sha256_prefix":"040c952ceb776b97","entry":"require_mood","repo":"jumelet/multiblimp","repo_kind":"official","path":"src/multiblimp/ud2um.py","file_url":"https://github.com/jumelet/multiblimp/blob/HEAD/src/multiblimp/ud2um.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":"040c952ceb776b97"}},{"code_sha256_prefix":"eee2967c488d0bd2","entry":"tree_has_typo","repo":"jumelet/multiblimp","repo_kind":"official","path":"src/multiblimp/treebank.py","file_url":"https://github.com/jumelet/multiblimp/blob/HEAD/src/multiblimp/treebank.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":"eee2967c488d0bd2"}},{"code_sha256_prefix":"990b239e22472ee3","entry":"balance_df","repo":"jumelet/multiblimp","repo_kind":"official","path":"src/multiblimp/downsample.py","file_url":"https://github.com/jumelet/multiblimp/blob/HEAD/src/multiblimp/downsample.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"990b239e22472ee3"}},{"code_sha256_prefix":"6c1ec2032b13637e","entry":"fetch_lang_candidates","repo":"jumelet/multiblimp","repo_kind":"official","path":"src/multiblimp/argparse.py","file_url":"https://github.com/jumelet/multiblimp/blob/HEAD/src/multiblimp/argparse.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6c1ec2032b13637e"}},{"code_sha256_prefix":"5a19249556829324","entry":"get_feature_combinations","repo":"jumelet/multiblimp","repo_kind":"official","path":"src/multiblimp/measure_agreement.py","file_url":"https://github.com/jumelet/multiblimp/blob/HEAD/src/multiblimp/measure_agreement.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5a19249556829324"}},{"code_sha256_prefix":"11b59d52083ba7b9","entry":"load_ud_features","repo":"jumelet/multiblimp","repo_kind":"official","path":"src/multiblimp/ud2um.py","file_url":"https://github.com/jumelet/multiblimp/blob/HEAD/src/multiblimp/ud2um.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"11b59d52083ba7b9"}},{"code_sha256_prefix":"26072aa0b2085c36","entry":"measure_orders","repo":"jumelet/multiblimp","repo_kind":"official","path":"src/multiblimp/measure_order.py","file_url":"https://github.com/jumelet/multiblimp/blob/HEAD/src/multiblimp/measure_order.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"26072aa0b2085c36"}},{"code_sha256_prefix":"3b7b0e7947c5df81","entry":"set_attractors","repo":"jumelet/multiblimp","repo_kind":"official","path":"src/multiblimp/downsample.py","file_url":"https://github.com/jumelet/multiblimp/blob/HEAD/src/multiblimp/downsample.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3b7b0e7947c5df81"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}