{"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/arabicmmlu-assessing-massive-multitask","title":"ArabicMMLU: Assessing Massive Multitask Language Understanding in Arabic","arxiv_id":"2402.12840","date":"2024-02-20","proceeding":null,"authors":["Fajri Koto","Haonan Li","Sara Shatnawi","Jad Doughman","Abdelrahman Boda Sadallah","Aisha Alraeesi","Khalid Almubarak","Zaid Alyafeai","Neha Sengupta","Shady Shehata","Nizar Habash","Preslav Nakov","Timothy Baldwin"],"abstract":"The focus of language model evaluation has transitioned towards reasoning and knowledge-intensive tasks, driven by advancements in pretraining large models. While state-of-the-art models are partially trained on large Arabic texts, evaluating their performance in Arabic remains challenging due to the limited availability of relevant datasets. To bridge this gap, we present \\datasetname{}, the first multi-task language understanding benchmark for the Arabic language, sourced from school exams across diverse educational levels in different countries spanning North Africa, the Levant, and the Gulf regions. Our data comprises 40 tasks and 14,575 multiple-choice questions in Modern Standard Arabic (MSA) and is carefully constructed by collaborating with native speakers in the region. Our comprehensive evaluations of 35 models reveal substantial room for improvement, particularly among the best open-source models. Notably, BLOOMZ, mT0, LLaMA2, and Falcon struggle to achieve a score of 50%, while even the top-performing Arabic-centric model only achieves a score of 62.3%.","url_abs":"https://arxiv.org/abs/2402.12840v2","url_pdf":"https://arxiv.org/pdf/2402.12840v2.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":"arabicmmlu-assessing-massive-multitask","repo_url":"https://github.com/mbzuai-nlp/arabicmmlu","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"arabicmmlu","task_name":"ArabicMMLU"},{"task_slug":"language-model-evaluation","task_name":"Language Model Evaluation"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"multi-task-language-understanding","task_name":"Multi-task Language Understanding"},{"task_slug":"multiple-choice","task_name":"Multiple-choice"}],"methods":[{"method_slug":"bloomz","method_name":"BLOOMZ"},{"method_slug":"focus","method_name":"Focus"},{"method_slug":"mt0","method_name":"mT0"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2402.12840","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.12840"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/mbzuai-nlp/arabicmmlu","reach":{"status":"ok"}}],"summary":{"ran_fixture":1,"ran":2,"unverified":3},"by_repo_kind":{"official":{"samples":6,"ran":3,"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":6,"samples":[{"code_sha256_prefix":"19f01570b0a18e2b","entry":"softmax","repo":"mbzuai-nlp/arabicmmlu","repo_kind":"official","path":"util_compute.py","file_url":"https://github.com/mbzuai-nlp/arabicmmlu/blob/HEAD/util_compute.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":2,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"19f01570b0a18e2b"}},{"code_sha256_prefix":"4b19c2af08f3ccb9","entry":"predict_classification_causal_by_letter","repo":"mbzuai-nlp/arabicmmlu","repo_kind":"official","path":"util_compute.py","file_url":"https://github.com/mbzuai-nlp/arabicmmlu/blob/HEAD/util_compute.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4b19c2af08f3ccb9"}},{"code_sha256_prefix":"de26a9f298ed9806","entry":"prepare_data_ar","repo":"mbzuai-nlp/arabicmmlu","repo_kind":"official","path":"util_prompt.py","file_url":"https://github.com/mbzuai-nlp/arabicmmlu/blob/HEAD/util_prompt.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"de26a9f298ed9806"}},{"code_sha256_prefix":"b13c640d52d81c89","entry":"predict_classification_mt0_by_letter","repo":"mbzuai-nlp/arabicmmlu","repo_kind":"official","path":"util_compute.py","file_url":"https://github.com/mbzuai-nlp/arabicmmlu/blob/HEAD/util_compute.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b13c640d52d81c89"}},{"code_sha256_prefix":"088f80fc18442c69","entry":"prepare_data","repo":"mbzuai-nlp/arabicmmlu","repo_kind":"official","path":"util_prompt.py","file_url":"https://github.com/mbzuai-nlp/arabicmmlu/blob/HEAD/util_prompt.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"088f80fc18442c69"}},{"code_sha256_prefix":"569db0c4fd316fca","entry":"prepare_data_en","repo":"mbzuai-nlp/arabicmmlu","repo_kind":"official","path":"util_prompt.py","file_url":"https://github.com/mbzuai-nlp/arabicmmlu/blob/HEAD/util_prompt.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"569db0c4fd316fca"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}