{"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/teaching-llama-a-new-language-through-cross","title":"Teaching Llama a New Language Through Cross-Lingual Knowledge Transfer","arxiv_id":"2404.04042","date":"2024-04-05","proceeding":null,"authors":["Hele-Andra Kuulmets","Taido Purason","Agnes Luhtaru","Mark Fishel"],"abstract":"This paper explores cost-efficient methods to adapt pretrained Large Language Models (LLMs) to new lower-resource languages, with a specific focus on Estonian. Leveraging the Llama 2 model, we investigate the impact of combining cross-lingual instruction-tuning with additional monolingual pretraining. Our results demonstrate that even a relatively small amount of additional monolingual pretraining followed by cross-lingual instruction-tuning significantly enhances results on Estonian. Furthermore, we showcase cross-lingual knowledge transfer from high-quality English instructions to Estonian, resulting in improvements in commonsense reasoning and multi-turn conversation capabilities. Our best model, named \\textsc{Llammas}, represents the first open-source instruction-following LLM for Estonian. Additionally, we publish Alpaca-est, the first general task instruction dataset for Estonia. These contributions mark the initial progress in the direction of developing open-source LLMs for Estonian.","url_abs":"https://arxiv.org/abs/2404.04042v1","url_pdf":"https://arxiv.org/pdf/2404.04042v1.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":"teaching-llama-a-new-language-through-cross","repo_url":"https://github.com/tartunlp/llammas","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"instruction-following","task_name":"Instruction Following"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"}],"methods":[{"method_slug":"focus","method_name":"Focus"},{"method_slug":"llama","method_name":"LLaMA"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2404.04042","atlas_url":"https://app.syntology.ai/?focus=2404.04042","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.04042"}},"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/tartunlp/llammas","reach":null}],"summary":{"ran_draft_wrong":3},"by_repo_kind":{"official":{"samples":3,"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":3,"samples":[{"code_sha256_prefix":"5ff5d6efbbdfd87b","entry":"encode_instruction_example","repo":"tartunlp/llammas","repo_kind":"official","path":"scripts/chat_data/instructions_to_chat.py","file_url":"https://github.com/tartunlp/llammas/blob/HEAD/scripts/chat_data/instructions_to_chat.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5ff5d6efbbdfd87b"}},{"code_sha256_prefix":"8bead2bc8cb5aff4","entry":"read_json","repo":"tartunlp/llammas","repo_kind":"official","path":"scripts/chat_data/instructions_to_chat.py","file_url":"https://github.com/tartunlp/llammas/blob/HEAD/scripts/chat_data/instructions_to_chat.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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8bead2bc8cb5aff4"}},{"code_sha256_prefix":"9d32f043536de9b2","entry":"read_jsonl","repo":"tartunlp/llammas","repo_kind":"official","path":"scripts/chat_data/instructions_to_chat.py","file_url":"https://github.com/tartunlp/llammas/blob/HEAD/scripts/chat_data/instructions_to_chat.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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9d32f043536de9b2"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}