{"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/instruct-align-teaching-novel-languages-with","title":"InstructAlign: High-and-Low Resource Language Alignment via Continual Crosslingual Instruction Tuning","arxiv_id":"2305.13627","date":"2023-05-23","proceeding":null,"authors":["Samuel Cahyawijaya","Holy Lovenia","Tiezheng Yu","Willy Chung","Pascale Fung"],"abstract":"Large language models (LLMs) that are tuned with instructions have demonstrated remarkable capabilities in various tasks and languages. However, their ability to generalize to underrepresented languages is limited due to the scarcity of available data. Additionally, directly adapting new languages to instruction-tuned LLMs can result in catastrophic forgetting, which leads to the loss of multitasking ability. To address this issue, we propose InstructAlign which uses continual crosslingual instruction tuning to enable LLMs to align new unseen languages with previously learned high-resource languages. Our results demonstrate the effectiveness of InstructAlign in enabling the model to understand low-resource languages with limited parallel data while preventing catastrophic forgetting. Our work contributes to the advancement of language adaptation methods, particularly for adapting instruction-tuned LLMs to underrepresented languages. Our code is released on https://github.com/HLTCHKUST/InstructAlign","url_abs":"https://arxiv.org/abs/2305.13627v2","url_pdf":"https://arxiv.org/pdf/2305.13627v2.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":"instruct-align-teaching-novel-languages-with","repo_url":"https://github.com/hltchkust/instructalign","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[],"methods":[{"method_slug":"align","method_name":"ALIGN"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2305.13627","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.13627"}},"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/hltchkust/instructalign","reach":null}],"summary":{"ran_draft_wrong":1,"unverified":3},"by_repo_kind":{"official":{"samples":4,"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":0,"samples":[{"code_sha256_prefix":"d1e96734ec6f84dd","entry":"to_prompt","repo":"hltchkust/instructalign","repo_kind":"official","path":"main_nlu_prompt.py","file_url":"https://github.com/hltchkust/instructalign/blob/HEAD/main_nlu_prompt.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":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d1e96734ec6f84dd"}},{"code_sha256_prefix":"efd81d324c9b6a6f","entry":"get_logprobs","repo":"hltchkust/instructalign","repo_kind":"official","path":"main_nlu_prompt.py","file_url":"https://github.com/hltchkust/instructalign/blob/HEAD/main_nlu_prompt.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"efd81d324c9b6a6f"}},{"code_sha256_prefix":"9239c0977078e7fe","entry":"get_prompt","repo":"hltchkust/instructalign","repo_kind":"official","path":"nlu_prompt.py","file_url":"https://github.com/hltchkust/instructalign/blob/HEAD/nlu_prompt.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"9239c0977078e7fe"}},{"code_sha256_prefix":"0e38ec2524e2b7d1","entry":"predict_classification","repo":"hltchkust/instructalign","repo_kind":"official","path":"main_nlu_prompt.py","file_url":"https://github.com/hltchkust/instructalign/blob/HEAD/main_nlu_prompt.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0e38ec2524e2b7d1"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}