{"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/mothello-when-do-cross-lingual-representation","title":"mOthello: When Do Cross-Lingual Representation Alignment and Cross-Lingual Transfer Emerge in Multilingual Models?","arxiv_id":"2404.12444","date":"2024-04-18","proceeding":null,"authors":["Tianze Hua","Tian Yun","Ellie Pavlick"],"abstract":"Many pretrained multilingual models exhibit cross-lingual transfer ability, which is often attributed to a learned language-neutral representation during pretraining. However, it remains unclear what factors contribute to the learning of a language-neutral representation, and whether the learned language-neutral representation suffices to facilitate cross-lingual transfer. We propose a synthetic task, Multilingual Othello (mOthello), as a testbed to delve into these two questions. We find that: (1) models trained with naive multilingual pretraining fail to learn a language-neutral representation across all input languages; (2) the introduction of \"anchor tokens\" (i.e., lexical items that are identical across languages) helps cross-lingual representation alignment; and (3) the learning of a language-neutral representation alone is not sufficient to facilitate cross-lingual transfer. Based on our findings, we propose a novel approach - multilingual pretraining with unified output space - that both induces the learning of language-neutral representation and facilitates cross-lingual transfer.","url_abs":"https://arxiv.org/abs/2404.12444v1","url_pdf":"https://arxiv.org/pdf/2404.12444v1.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":"mothello-when-do-cross-lingual-representation","repo_url":"https://github.com/ethahtz/multilingual_othello","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"cross-lingual-transfer","task_name":"Cross-Lingual Transfer"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2404.12444","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.12444"}},"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/ethahtz/multilingual_othello","reach":null}],"summary":{"ran_fixture":3,"ran_honours":1,"ran":1},"by_repo_kind":{"official":{"samples":5,"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":0,"samples":[{"code_sha256_prefix":"b6813e2d44c37738","entry":"countPrefix","repo":"ethahtz/multilingual_othello","repo_kind":"official","path":"ft_experiment.py","file_url":"https://github.com/ethahtz/multilingual_othello/blob/HEAD/ft_experiment.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b6813e2d44c37738"}},{"code_sha256_prefix":"1a1c7d033a9773e6","entry":"count_state_accuracy","repo":"ethahtz/multilingual_othello","repo_kind":"official","path":"metrics.py","file_url":"https://github.com/ethahtz/multilingual_othello/blob/HEAD/metrics.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1a1c7d033a9773e6"}},{"code_sha256_prefix":"c85d05f1e81b48a1","entry":"get_random_subset","repo":"ethahtz/multilingual_othello","repo_kind":"official","path":"ft_experiment.py","file_url":"https://github.com/ethahtz/multilingual_othello/blob/HEAD/ft_experiment.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c85d05f1e81b48a1"}},{"code_sha256_prefix":"38615900da6c9437","entry":"heatmap","repo":"ethahtz/multilingual_othello","repo_kind":"official","path":"metrics.py","file_url":"https://github.com/ethahtz/multilingual_othello/blob/HEAD/metrics.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"38615900da6c9437"}},{"code_sha256_prefix":"7d901603def7e89d","entry":"probe_logits2boardstate","repo":"ethahtz/multilingual_othello","repo_kind":"official","path":"metrics.py","file_url":"https://github.com/ethahtz/multilingual_othello/blob/HEAD/metrics.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7d901603def7e89d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}