{"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/how-multilingual-is-multilingual-llm","title":"How Vocabulary Sharing Facilitates Multilingualism in LLaMA?","arxiv_id":"2311.09071","date":"2023-11-15","proceeding":null,"authors":["Fei Yuan","Shuai Yuan","Zhiyong Wu","Lei LI"],"abstract":"Large Language Models (LLMs), often show strong performance on English tasks, while exhibiting limitations on other languages. What is an LLM's multilingual capability when it is trained only on certain languages? The underlying mechanism remains unclear. This study endeavors to examine the multilingual capability of LLMs from the vocabulary sharing perspective by conducting an exhaustive analysis across 101 languages. Through the investigation of the performance gap before and after embedding fine-tuning, we discovered four distinct quadrants. By delving into each quadrant we provide actionable and efficient guidelines for tuning these languages. Extensive experiments reveal that existing LLMs possess multilingual capabilities that surpass our expectations, and we can significantly improve the multilingual performance of LLMs based on these attributes of each quadrant~\\footnote{\\url{https://github.com/CONE-MT/Vocabulary-Sharing-Facilitates-Multilingualism}.}.","url_abs":"https://arxiv.org/abs/2311.09071v2","url_pdf":"https://arxiv.org/pdf/2311.09071v2.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":"how-multilingual-is-multilingual-llm","repo_url":"https://github.com/cone-mt/vocabulary-sharing-facilitates-multilingualism","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2311.09071","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.09071"}},"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/cone-mt/vocabulary-sharing-facilitates-multilingualism","reach":{"status":"ok"}}],"summary":{"ran":4,"ran_draft_wrong":1,"unverified":4},"by_repo_kind":{"official":{"samples":9,"ran":5,"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":"a0ea69023061da19","entry":"get_args","repo":"cone-mt/vocabulary-sharing-facilitates-multilingualism","repo_kind":"official","path":"Shorten/inference.py","file_url":"https://github.com/cone-mt/vocabulary-sharing-facilitates-multilingualism/blob/HEAD/Shorten/inference.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":"a0ea69023061da19"}},{"code_sha256_prefix":"3c11ff2df61dfc87","entry":"load_module_from_path","repo":"cone-mt/vocabulary-sharing-facilitates-multilingualism","repo_kind":"official","path":"Shorten/inference.py","file_url":"https://github.com/cone-mt/vocabulary-sharing-facilitates-multilingualism/blob/HEAD/Shorten/inference.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":"3c11ff2df61dfc87"}},{"code_sha256_prefix":"2a686c7dfc4f6740","entry":"read_input","repo":"cone-mt/vocabulary-sharing-facilitates-multilingualism","repo_kind":"official","path":"Shorten/src/datasets/flores.py","file_url":"https://github.com/cone-mt/vocabulary-sharing-facilitates-multilingualism/blob/HEAD/Shorten/src/datasets/flores.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2a686c7dfc4f6740"}},{"code_sha256_prefix":"225017f452f0b254","entry":"read_instruct","repo":"cone-mt/vocabulary-sharing-facilitates-multilingualism","repo_kind":"official","path":"Shorten/src/datasets/flores.py","file_url":"https://github.com/cone-mt/vocabulary-sharing-facilitates-multilingualism/blob/HEAD/Shorten/src/datasets/flores.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":"225017f452f0b254"}},{"code_sha256_prefix":"9826ffe893c1e6a5","entry":"read_yaml_file","repo":"cone-mt/vocabulary-sharing-facilitates-multilingualism","repo_kind":"official","path":"Shorten/inference.py","file_url":"https://github.com/cone-mt/vocabulary-sharing-facilitates-multilingualism/blob/HEAD/Shorten/inference.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":"9826ffe893c1e6a5"}},{"code_sha256_prefix":"ebf5903eb8c9714b","entry":"dataloader","repo":"cone-mt/vocabulary-sharing-facilitates-multilingualism","repo_kind":"official","path":"Shorten/src/datasets/ceval.py","file_url":"https://github.com/cone-mt/vocabulary-sharing-facilitates-multilingualism/blob/HEAD/Shorten/src/datasets/ceval.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":"ebf5903eb8c9714b"}},{"code_sha256_prefix":"daf18542ed5cb613","entry":"get_embedding_tensor_and_tokenizer","repo":"cone-mt/vocabulary-sharing-facilitates-multilingualism","repo_kind":"official","path":"Shorten/src/datasets/common.py","file_url":"https://github.com/cone-mt/vocabulary-sharing-facilitates-multilingualism/blob/HEAD/Shorten/src/datasets/common.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":"daf18542ed5cb613"}},{"code_sha256_prefix":"8fdec934bb8ce2a2","entry":"get_lang_instruction","repo":"cone-mt/vocabulary-sharing-facilitates-multilingualism","repo_kind":"official","path":"Shorten/src/datasets/flores.py","file_url":"https://github.com/cone-mt/vocabulary-sharing-facilitates-multilingualism/blob/HEAD/Shorten/src/datasets/flores.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":"8fdec934bb8ce2a2"}},{"code_sha256_prefix":"3598ea9b0954beb4","entry":"merge_tokenizer","repo":"cone-mt/vocabulary-sharing-facilitates-multilingualism","repo_kind":"official","path":"run_clm_ft_extend_vocab.py","file_url":"https://github.com/cone-mt/vocabulary-sharing-facilitates-multilingualism/blob/HEAD/run_clm_ft_extend_vocab.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":"3598ea9b0954beb4"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}