{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:KFVOTV3CRR6KVRTTEFUNCFNQ7R","short_pith_number":"pith:KFVOTV3C","schema_version":"1.0","canonical_sha256":"516ae9d7628c7caac6732168d115b0fc5796f0bdcf559ddd58d8f8f41536808b","source":{"kind":"arxiv","id":"2505.18673","version":1},"attestation_state":"computed","paper":{"title":"Cross-Lingual Pitfalls: Automatic Probing Cross-Lingual Weakness of Multilingual Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jieyu Zhao, Meng Jiang, Xiangliang Zhang, Xiuying Chen, Yanbo Wang, Yue Huang, Zixiang Xu","submitted_at":"2025-05-24T12:31:27Z","abstract_excerpt":"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 "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2505.18673","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-24T12:31:27Z","cross_cats_sorted":[],"title_canon_sha256":"031d5b7f2f3f7f133c5222b88537ec20777f6ecb70fbba11484202f9704be2e5","abstract_canon_sha256":"09443cccb42cda97b85058592be744400b7b2134382a971bc61c54acb778f319"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:17.690697Z","signature_b64":"xP+d2uSmwFoubhGdjp7LUCIZwKaBc2hAKRIdaluHnXTpKvNq+MmHOzrb37fcfXu+nK+AQSbsdQ38m9xv6QGhCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"516ae9d7628c7caac6732168d115b0fc5796f0bdcf559ddd58d8f8f41536808b","last_reissued_at":"2026-07-05T11:09:17.690192Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:17.690192Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cross-Lingual Pitfalls: Automatic Probing Cross-Lingual Weakness of Multilingual Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jieyu Zhao, Meng Jiang, Xiangliang Zhang, Xiuying Chen, Yanbo Wang, Yue Huang, Zixiang Xu","submitted_at":"2025-05-24T12:31:27Z","abstract_excerpt":"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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.18673","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2505.18673/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2505.18673","created_at":"2026-07-05T11:09:17.690253+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.18673v1","created_at":"2026-07-05T11:09:17.690253+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.18673","created_at":"2026-07-05T11:09:17.690253+00:00"},{"alias_kind":"pith_short_12","alias_value":"KFVOTV3CRR6K","created_at":"2026-07-05T11:09:17.690253+00:00"},{"alias_kind":"pith_short_16","alias_value":"KFVOTV3CRR6KVRTT","created_at":"2026-07-05T11:09:17.690253+00:00"},{"alias_kind":"pith_short_8","alias_value":"KFVOTV3C","created_at":"2026-07-05T11:09:17.690253+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KFVOTV3CRR6KVRTTEFUNCFNQ7R","json":"https://pith.science/pith/KFVOTV3CRR6KVRTTEFUNCFNQ7R.json","graph_json":"https://pith.science/api/pith-number/KFVOTV3CRR6KVRTTEFUNCFNQ7R/graph.json","events_json":"https://pith.science/api/pith-number/KFVOTV3CRR6KVRTTEFUNCFNQ7R/events.json","paper":"https://pith.science/paper/KFVOTV3C"},"agent_actions":{"view_html":"https://pith.science/pith/KFVOTV3CRR6KVRTTEFUNCFNQ7R","download_json":"https://pith.science/pith/KFVOTV3CRR6KVRTTEFUNCFNQ7R.json","view_paper":"https://pith.science/paper/KFVOTV3C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.18673&json=true","fetch_graph":"https://pith.science/api/pith-number/KFVOTV3CRR6KVRTTEFUNCFNQ7R/graph.json","fetch_events":"https://pith.science/api/pith-number/KFVOTV3CRR6KVRTTEFUNCFNQ7R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KFVOTV3CRR6KVRTTEFUNCFNQ7R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KFVOTV3CRR6KVRTTEFUNCFNQ7R/action/storage_attestation","attest_author":"https://pith.science/pith/KFVOTV3CRR6KVRTTEFUNCFNQ7R/action/author_attestation","sign_citation":"https://pith.science/pith/KFVOTV3CRR6KVRTTEFUNCFNQ7R/action/citation_signature","submit_replication":"https://pith.science/pith/KFVOTV3CRR6KVRTTEFUNCFNQ7R/action/replication_record"}},"created_at":"2026-07-05T11:09:17.690253+00:00","updated_at":"2026-07-05T11:09:17.690253+00:00"}