{"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/emma-500-enhancing-massively-multilingual","title":"EMMA-500: Enhancing Massively Multilingual Adaptation of Large Language Models","arxiv_id":"2409.17892","date":"2024-09-26","proceeding":null,"authors":["Shaoxiong Ji","Zihao Li","Indraneil Paul","Jaakko Paavola","Peiqin Lin","Pinzhen Chen","Dayyán O'Brien","Hengyu Luo","Hinrich Schütze","Jörg Tiedemann","Barry Haddow"],"abstract":"In this work, we introduce EMMA-500, a large-scale multilingual language model continue-trained on texts across 546 languages designed for enhanced multilingual performance, focusing on improving language coverage for low-resource languages. To facilitate continual pre-training, we compile the MaLA corpus, a comprehensive multilingual dataset enriched with curated datasets across diverse domains. Leveraging this corpus, we conduct extensive continual pre-training of the Llama 2 7B model, resulting in EMMA-500, which demonstrates robust performance across a wide collection of benchmarks, including a comprehensive set of multilingual tasks and PolyWrite, an open-ended generation benchmark developed in this study. Our results highlight the effectiveness of continual pre-training in expanding large language models' language capacity, particularly for underrepresented languages, demonstrating significant gains in cross-lingual transfer, task generalization, and language adaptability.","url_abs":"https://arxiv.org/abs/2409.17892v1","url_pdf":"https://arxiv.org/pdf/2409.17892v1.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":"emma-500-enhancing-massively-multilingual","repo_url":"https://github.com/MaLA-LM/emma-500","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"cross-lingual-transfer","task_name":"Cross-Lingual Transfer"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"}],"methods":[{"method_slug":"llama","method_name":"LLaMA"},{"method_slug":"set","method_name":"SET"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2409.17892","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.17892"}},"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/MaLA-LM/emma-500","reach":{"status":"ok"}}],"summary":{"ran":8,"unverified":1},"by_repo_kind":{"official":{"samples":9,"ran":8,"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":9,"samples":[{"code_sha256_prefix":"4eb484b8f5cf861a","entry":"format_base_model_sentence_pair","repo":"MaLA-LM/emma-500","repo_kind":"official","path":"evaluation/Flores-200/eval_flores200.py","file_url":"https://github.com/MaLA-LM/emma-500/blob/HEAD/evaluation/Flores-200/eval_flores200.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4eb484b8f5cf861a"}},{"code_sha256_prefix":"83169f3b1236b647","entry":"format_text_with_examples","repo":"MaLA-LM/emma-500","repo_kind":"official","path":"evaluation/Sib-200/eval_sib200.py","file_url":"https://github.com/MaLA-LM/emma-500/blob/HEAD/evaluation/Sib-200/eval_sib200.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":"83169f3b1236b647"}},{"code_sha256_prefix":"68a39991e6b6188d","entry":"generate_examples","repo":"MaLA-LM/emma-500","repo_kind":"official","path":"evaluation/Sib-200/eval_sib200.py","file_url":"https://github.com/MaLA-LM/emma-500/blob/HEAD/evaluation/Sib-200/eval_sib200.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":"68a39991e6b6188d"}},{"code_sha256_prefix":"12d986515be1710d","entry":"get_self_bleu_score","repo":"MaLA-LM/emma-500","repo_kind":"official","path":"evaluation/Aya/evaluate.py","file_url":"https://github.com/MaLA-LM/emma-500/blob/HEAD/evaluation/Aya/evaluate.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":"12d986515be1710d"}},{"code_sha256_prefix":"cfcff66fced80dfc","entry":"process_file","repo":"MaLA-LM/emma-500","repo_kind":"official","path":"evaluation/Aya/evaluate.py","file_url":"https://github.com/MaLA-LM/emma-500/blob/HEAD/evaluation/Aya/evaluate.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":"cfcff66fced80dfc"}},{"code_sha256_prefix":"47ad7e8829ffe863","entry":"read_jsonl","repo":"MaLA-LM/emma-500","repo_kind":"official","path":"evaluation/Aya/evaluate.py","file_url":"https://github.com/MaLA-LM/emma-500/blob/HEAD/evaluation/Aya/evaluate.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":"47ad7e8829ffe863"}},{"code_sha256_prefix":"a55fd1d0ebf78af5","entry":"read_sentences_from_file","repo":"MaLA-LM/emma-500","repo_kind":"official","path":"evaluation/Aya/eval_aya.py","file_url":"https://github.com/MaLA-LM/emma-500/blob/HEAD/evaluation/Aya/eval_aya.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":"a55fd1d0ebf78af5"}},{"code_sha256_prefix":"7aada1cb5e2cbbbb","entry":"sample_in_context_examples","repo":"MaLA-LM/emma-500","repo_kind":"official","path":"evaluation/Flores-200/eval_flores200.py","file_url":"https://github.com/MaLA-LM/emma-500/blob/HEAD/evaluation/Flores-200/eval_flores200.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":"7aada1cb5e2cbbbb"}},{"code_sha256_prefix":"7b71e88b9faa2f99","entry":"get_ans","repo":"MaLA-LM/emma-500","repo_kind":"official","path":"evaluation/Sib-200/eval_sib200.py","file_url":"https://github.com/MaLA-LM/emma-500/blob/HEAD/evaluation/Sib-200/eval_sib200.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":"7b71e88b9faa2f99"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}