{"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/cross-lingual-pitfalls-automatic-probing","title":"Cross-Lingual Pitfalls: Automatic Probing Cross-Lingual Weakness of Multilingual Large Language Models","arxiv_id":"2505.18673","date":"2025-05-24","proceeding":null,"authors":["Zixiang Xu","Yanbo Wang","Yue Huang","Xiuying Chen","Jieyu Zhao","Meng Jiang","Xiangliang Zhang"],"abstract":"Large Language Models (LLMs) have achieved remarkable success in Natural Language Processing (NLP), yet their cross-lingual performance consistency remains a significant challenge. This paper introduces a novel methodology for efficiently identifying inherent cross-lingual weaknesses in LLMs. Our approach leverages beam search and LLM-based simulation to generate bilingual question pairs that expose performance discrepancies between English and target languages. We construct a new dataset of over 6,000 bilingual pairs across 16 languages using this methodology, demonstrating its effectiveness in revealing weaknesses even in state-of-the-art models. The extensive experiments demonstrate that our method precisely and cost-effectively pinpoints cross-lingual weaknesses, consistently revealing over 50\\% accuracy drops in target languages across a wide range of models. Moreover, further experiments investigate the relationship between linguistic similarity and cross-lingual weaknesses, revealing that linguistically related languages share similar performance patterns and benefit from targeted post-training. Code is available at https://github.com/xzx34/Cross-Lingual-Pitfalls.","url_abs":"https://arxiv.org/abs/2505.18673v1","url_pdf":"https://arxiv.org/pdf/2505.18673v1.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":"cross-lingual-pitfalls-automatic-probing","repo_url":"https://github.com/xzx34/cross-lingual-pitfalls","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2505.18673","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.18673"}},"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/xzx34/Cross-Lingual-Pitfalls","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":1,"unverified":14},"by_repo_kind":{"official":{"samples":15,"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":"ee50a40e401c2b10","entry":"read_json","repo":"xzx34/Cross-Lingual-Pitfalls","repo_kind":"official","path":"visualization.py","file_url":"https://github.com/xzx34/Cross-Lingual-Pitfalls/blob/HEAD/visualization.py","link_basis":"harvester_set","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":"ee50a40e401c2b10"}},{"code_sha256_prefix":"9db9d1e2d0dd0bab","entry":"check_format","repo":"xzx34/Cross-Lingual-Pitfalls","repo_kind":"official","path":"utils/check.py","file_url":"https://github.com/xzx34/Cross-Lingual-Pitfalls/blob/HEAD/utils/check.py","link_basis":"harvester_set","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":"9db9d1e2d0dd0bab"}},{"code_sha256_prefix":"4ab54a84ec558774","entry":"check_multiple","repo":"xzx34/Cross-Lingual-Pitfalls","repo_kind":"official","path":"utils/check.py","file_url":"https://github.com/xzx34/Cross-Lingual-Pitfalls/blob/HEAD/utils/check.py","link_basis":"harvester_set","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":"4ab54a84ec558774"}},{"code_sha256_prefix":"60f1e77421c373b1","entry":"check_semantic","repo":"xzx34/Cross-Lingual-Pitfalls","repo_kind":"official","path":"utils/check.py","file_url":"https://github.com/xzx34/Cross-Lingual-Pitfalls/blob/HEAD/utils/check.py","link_basis":"harvester_set","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":"60f1e77421c373b1"}},{"code_sha256_prefix":"99fb32bf3b96639a","entry":"extract_question","repo":"xzx34/Cross-Lingual-Pitfalls","repo_kind":"official","path":"utils/prompt.py","file_url":"https://github.com/xzx34/Cross-Lingual-Pitfalls/blob/HEAD/utils/prompt.py","link_basis":"harvester_set","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":"99fb32bf3b96639a"}},{"code_sha256_prefix":"d079e9d72790326b","entry":"generate_ideas","repo":"xzx34/Cross-Lingual-Pitfalls","repo_kind":"official","path":"utils/ideas.py","file_url":"https://github.com/xzx34/Cross-Lingual-Pitfalls/blob/HEAD/utils/ideas.py","link_basis":"harvester_set","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":"d079e9d72790326b"}},{"code_sha256_prefix":"b359e98e028239a3","entry":"generate_question","repo":"xzx34/Cross-Lingual-Pitfalls","repo_kind":"official","path":"utils/question.py","file_url":"https://github.com/xzx34/Cross-Lingual-Pitfalls/blob/HEAD/utils/question.py","link_basis":"harvester_set","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":"b359e98e028239a3"}},{"code_sha256_prefix":"2f6e51b4c650ee0c","entry":"get_category","repo":"xzx34/Cross-Lingual-Pitfalls","repo_kind":"official","path":"utils/prompt.py","file_url":"https://github.com/xzx34/Cross-Lingual-Pitfalls/blob/HEAD/utils/prompt.py","link_basis":"harvester_set","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":"2f6e51b4c650ee0c"}},{"code_sha256_prefix":"43d6f9f58b1cdd6e","entry":"get_distraction","repo":"xzx34/Cross-Lingual-Pitfalls","repo_kind":"official","path":"utils/prompt.py","file_url":"https://github.com/xzx34/Cross-Lingual-Pitfalls/blob/HEAD/utils/prompt.py","link_basis":"harvester_set","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":"43d6f9f58b1cdd6e"}},{"code_sha256_prefix":"1ab2a84c0b4c9b0a","entry":"num_tokens_from_string","repo":"xzx34/Cross-Lingual-Pitfalls","repo_kind":"official","path":"utils/tools.py","file_url":"https://github.com/xzx34/Cross-Lingual-Pitfalls/blob/HEAD/utils/tools.py","link_basis":"harvester_set","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":"1ab2a84c0b4c9b0a"}},{"code_sha256_prefix":"8ee594df16d22dd6","entry":"retry_on_failure","repo":"xzx34/Cross-Lingual-Pitfalls","repo_kind":"official","path":"utils/tools.py","file_url":"https://github.com/xzx34/Cross-Lingual-Pitfalls/blob/HEAD/utils/tools.py","link_basis":"harvester_set","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":"8ee594df16d22dd6"}},{"code_sha256_prefix":"6af661cb96adc80d","entry":"simulate","repo":"xzx34/Cross-Lingual-Pitfalls","repo_kind":"official","path":"utils/answers.py","file_url":"https://github.com/xzx34/Cross-Lingual-Pitfalls/blob/HEAD/utils/answers.py","link_basis":"harvester_set","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":"6af661cb96adc80d"}},{"code_sha256_prefix":"0b85931c9d896479","entry":"token_logger_decorator","repo":"xzx34/Cross-Lingual-Pitfalls","repo_kind":"official","path":"utils/tools.py","file_url":"https://github.com/xzx34/Cross-Lingual-Pitfalls/blob/HEAD/utils/tools.py","link_basis":"harvester_set","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":"0b85931c9d896479"}},{"code_sha256_prefix":"67987740b72e6ef2","entry":"translate_question","repo":"xzx34/Cross-Lingual-Pitfalls","repo_kind":"official","path":"utils/translate.py","file_url":"https://github.com/xzx34/Cross-Lingual-Pitfalls/blob/HEAD/utils/translate.py","link_basis":"harvester_set","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":"67987740b72e6ef2"}},{"code_sha256_prefix":"a6fd2a473f66f0c1","entry":"translate_text","repo":"xzx34/Cross-Lingual-Pitfalls","repo_kind":"official","path":"utils/translate.py","file_url":"https://github.com/xzx34/Cross-Lingual-Pitfalls/blob/HEAD/utils/translate.py","link_basis":"harvester_set","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":"a6fd2a473f66f0c1"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}