{"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/exams-a-multi-subject-high-school","title":"EXAMS: A Multi-Subject High School Examinations Dataset for Cross-Lingual and Multilingual Question Answering","arxiv_id":"2011.03080","date":"2020-11-05","proceeding":"EMNLP 2020 11","authors":["Momchil Hardalov","Todor Mihaylov","Dimitrina Zlatkova","Yoan Dinkov","Ivan Koychev","Preslav Nakov"],"abstract":"We propose EXAMS -- a new benchmark dataset for cross-lingual and multilingual question answering for high school examinations. We collected more than 24,000 high-quality high school exam questions in 16 languages, covering 8 language families and 24 school subjects from Natural Sciences and Social Sciences, among others. EXAMS offers a fine-grained evaluation framework across multiple languages and subjects, which allows precise analysis and comparison of various models. We perform various experiments with existing top-performing multilingual pre-trained models and we show that EXAMS offers multiple challenges that require multilingual knowledge and reasoning in multiple domains. We hope that EXAMS will enable researchers to explore challenging reasoning and knowledge transfer methods and pre-trained models for school question answering in various languages which was not possible before. The data, code, pre-trained models, and evaluation are available at https://github.com/mhardalov/exams-qa.","url_abs":"https://arxiv.org/abs/2011.03080v1","url_pdf":"https://arxiv.org/pdf/2011.03080v1.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":"exams-a-multi-subject-high-school","repo_url":"https://github.com/mhardalov/exams-qa","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"exams-a-multi-subject-high-school","repo_url":"https://github.com/checkstep/mole-stance","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"}],"methods":[],"datasets_introduced":[{"slug":"exams","name":"EXAMS","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2011.03080","atlas_url":"https://app.syntology.ai/?focus=2011.03080","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2011.03080"}},"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/checkstep/mole-stance","reach":{"status":"unanswered"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/mhardalov/exams-qa","reach":null}],"summary":{"ran_draft_wrong":1,"unverified":2},"by_repo_kind":{"official":{"samples":1,"ran":1,"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":3,"samples":[{"code_sha256_prefix":"a8e37b64d3b97cca","entry":"eval_exams","repo":"mhardalov/exams-qa","repo_kind":"official","path":"scripts/evaluation/evaluate_exams.py","file_url":"https://github.com/mhardalov/exams-qa/blob/HEAD/scripts/evaluation/evaluate_exams.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"CC-BY-SA-4.0","inline_ok":false,"mcp_get_code":{"code_sha256":"a8e37b64d3b97cca"}},{"code_sha256_prefix":"0a546b305d274996","entry":"select_field","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"0a546b305d274996"}},{"code_sha256_prefix":"3c241ecfe3749a6d","entry":"simple_accuracy","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"3c241ecfe3749a6d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}