{"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/exploring-intrinsic-language-specific","title":"Exploring Intrinsic Language-specific Subspaces in Fine-tuning Multilingual Neural Machine Translation","arxiv_id":"2409.05224","date":"2024-09-08","proceeding":null,"authors":["Zhe Cao","Zhi Qu","Hidetaka Kamigaito","Taro Watanabe"],"abstract":"Multilingual neural machine translation models support fine-tuning hundreds of languages simultaneously. However, fine-tuning on full parameters solely is inefficient potentially leading to negative interactions among languages. In this work, we demonstrate that the fine-tuning for a language occurs in its intrinsic language-specific subspace with a tiny fraction of entire parameters. Thus, we propose language-specific LoRA to isolate intrinsic language-specific subspaces. Furthermore, we propose architecture learning techniques and introduce a gradual pruning schedule during fine-tuning to exhaustively explore the optimal setting and the minimal intrinsic subspaces for each language, resulting in a lightweight yet effective fine-tuning procedure. The experimental results on a 12-language subset and a 30-language subset of FLORES-101 show that our methods not only outperform full-parameter fine-tuning up to 2.25 spBLEU scores but also reduce trainable parameters to $0.4\\%$ for high and medium-resource languages and $1.6\\%$ for low-resource ones.","url_abs":"https://arxiv.org/abs/2409.05224v1","url_pdf":"https://arxiv.org/pdf/2409.05224v1.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":"exploring-intrinsic-language-specific","repo_url":"https://github.com/spike0924/lslo","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"machine-translation","task_name":"Machine Translation"}],"methods":[{"method_slug":"pruning","method_name":"Pruning"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2409.05224","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.05224"}},"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":"deterministic:regex_extraction","url":"https://github.com/Spike0924/LSLo","reach":null}],"summary":{"ran":2},"by_repo_kind":{"official":{"samples":2,"ran":2,"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":2,"samples":[{"code_sha256_prefix":"9811894976bf230f","entry":"LangSpecLora","repo":"Spike0924/LSLo","repo_kind":"official","path":"global_pruning_langspec_transformer_lora_src/global_pruning_langspec_transformer_lora/modules/lora.py","file_url":"https://github.com/Spike0924/LSLo/blob/HEAD/global_pruning_langspec_transformer_lora_src/global_pruning_langspec_transformer_lora/modules/lora.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9811894976bf230f"}},{"code_sha256_prefix":"b7782d1e634cd26a","entry":"Lora","repo":"Spike0924/LSLo","repo_kind":"official","path":"global_pruning_langspec_transformer_lora_src/global_pruning_langspec_transformer_lora/modules/lora.py","file_url":"https://github.com/Spike0924/LSLo/blob/HEAD/global_pruning_langspec_transformer_lora_src/global_pruning_langspec_transformer_lora/modules/lora.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b7782d1e634cd26a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}