{"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-the-relationship-between-alignment","title":"Exploring the Relationship between Alignment and Cross-lingual Transfer in Multilingual Transformers","arxiv_id":"2306.02790","date":"2023-06-05","proceeding":null,"authors":["Félix Gaschi","Patricio Cerda","Parisa Rastin","Yannick Toussaint"],"abstract":"Without any explicit cross-lingual training data, multilingual language models can achieve cross-lingual transfer. One common way to improve this transfer is to perform realignment steps before fine-tuning, i.e., to train the model to build similar representations for pairs of words from translated sentences. But such realignment methods were found to not always improve results across languages and tasks, which raises the question of whether aligned representations are truly beneficial for cross-lingual transfer. We provide evidence that alignment is actually significantly correlated with cross-lingual transfer across languages, models and random seeds. We show that fine-tuning can have a significant impact on alignment, depending mainly on the downstream task and the model. Finally, we show that realignment can, in some instances, improve cross-lingual transfer, and we identify conditions in which realignment methods provide significant improvements. Namely, we find that realignment works better on tasks for which alignment is correlated with cross-lingual transfer when generalizing to a distant language and with smaller models, as well as when using a bilingual dictionary rather than FastAlign to extract realignment pairs. For example, for POS-tagging, between English and Arabic, realignment can bring a +15.8 accuracy improvement on distilmBERT, even outperforming XLM-R Large by 1.7. We thus advocate for further research on realignment methods for smaller multilingual models as an alternative to scaling.","url_abs":"https://arxiv.org/abs/2306.02790v1","url_pdf":"https://arxiv.org/pdf/2306.02790v1.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-the-relationship-between-alignment","repo_url":"https://github.com/posos-tech/multilingual-alignment-and-transfer","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"cross-lingual-transfer","task_name":"Cross-Lingual Transfer"},{"task_slug":"pos","task_name":"POS"},{"task_slug":"pos-tagging","task_name":"POS Tagging"},{"task_slug":"xlm-r","task_name":"XLM-R"}],"methods":[{"method_slug":"xlm-r","method_name":"XLM-R"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2306.02790","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.02790"}},"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/posos-tech/multilingual-alignment-and-transfer","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":7},"by_repo_kind":{"official":{"samples":7,"ran":0,"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":"ca2784cbd62536cf","entry":"bitfit","repo":"posos-tech/multilingual-alignment-and-transfer","repo_kind":"official","path":"multilingual_eval/models/partial_freezes.py","file_url":"https://github.com/posos-tech/multilingual-alignment-and-transfer/blob/HEAD/multilingual_eval/models/partial_freezes.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ca2784cbd62536cf"}},{"code_sha256_prefix":"f08dba90e421e304","entry":"load_biomedical_wmt19","repo":"posos-tech/multilingual-alignment-and-transfer","repo_kind":"official","path":"multilingual_eval/data.py","file_url":"https://github.com/posos-tech/multilingual-alignment-and-transfer/blob/HEAD/multilingual_eval/data.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f08dba90e421e304"}},{"code_sha256_prefix":"2a6b57ba2d3b09cf","entry":"load_europarl","repo":"posos-tech/multilingual-alignment-and-transfer","repo_kind":"official","path":"multilingual_eval/data.py","file_url":"https://github.com/posos-tech/multilingual-alignment-and-transfer/blob/HEAD/multilingual_eval/data.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2a6b57ba2d3b09cf"}},{"code_sha256_prefix":"e9a42840640e9263","entry":"load_from_fastalign_input","repo":"posos-tech/multilingual-alignment-and-transfer","repo_kind":"official","path":"multilingual_eval/data.py","file_url":"https://github.com/posos-tech/multilingual-alignment-and-transfer/blob/HEAD/multilingual_eval/data.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e9a42840640e9263"}},{"code_sha256_prefix":"1212dede4f4a90d2","entry":"post_on_slack","repo":"posos-tech/multilingual-alignment-and-transfer","repo_kind":"official","path":"multilingual_eval/loggers.py","file_url":"https://github.com/posos-tech/multilingual-alignment-and-transfer/blob/HEAD/multilingual_eval/loggers.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1212dede4f4a90d2"}},{"code_sha256_prefix":"6b9c69ee7a3fcfae","entry":"remove_batch_dimension","repo":"posos-tech/multilingual-alignment-and-transfer","repo_kind":"official","path":"multilingual_eval/models/utils.py","file_url":"https://github.com/posos-tech/multilingual-alignment-and-transfer/blob/HEAD/multilingual_eval/models/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6b9c69ee7a3fcfae"}},{"code_sha256_prefix":"49acb57287ba20d1","entry":"sum_ranges_and_put_together","repo":"posos-tech/multilingual-alignment-and-transfer","repo_kind":"official","path":"multilingual_eval/models/utils.py","file_url":"https://github.com/posos-tech/multilingual-alignment-and-transfer/blob/HEAD/multilingual_eval/models/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"49acb57287ba20d1"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}