{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LKRO3PNAVWOYMMEV4OZI5RTT43","short_pith_number":"pith:LKRO3PNA","schema_version":"1.0","canonical_sha256":"5aa2edbda0ad9d863095e3b28ec673e6f4e0afa0f0ad1f782b49ec5203b91e4f","source":{"kind":"arxiv","id":"2402.11485","version":2},"attestation_state":"computed","paper":{"title":"LEIA: Facilitating Cross-lingual Knowledge Transfer in Language Models with Entity-based Data Augmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Ikuya Yamada, Ryokan Ri","submitted_at":"2024-02-18T07:24:34Z","abstract_excerpt":"Adapting English-based large language models (LLMs) to other languages has become increasingly popular due to the efficiency and potential of cross-lingual transfer. However, existing language adaptation methods often overlook the benefits of cross-lingual supervision. In this study, we introduce LEIA, a language adaptation tuning method that utilizes Wikipedia entity names aligned across languages. This method involves augmenting the target language corpus with English entity names and training the model using left-to-right language modeling. We assess LEIA on diverse question answering datas"},"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":"2402.11485","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-18T07:24:34Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"1d02e0c450ac556db63a16977ae47f12538a31ead3ea790049509ff9487c0b4e","abstract_canon_sha256":"3068be5ad3ecd0f4421f4eb93cfac025ebbfc24cdbc7b1c1a212b025b045916b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:28:06.184958Z","signature_b64":"s/iCtOFCTg1+m3bkveaOowTs3zzaKeEWgvCBe3JkIR+hCWitZ5gaLqWJBdIvYXFOL/0EaAQuS0U9Y2cHHQH0Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5aa2edbda0ad9d863095e3b28ec673e6f4e0afa0f0ad1f782b49ec5203b91e4f","last_reissued_at":"2026-07-05T08:28:06.184542Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:28:06.184542Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LEIA: Facilitating Cross-lingual Knowledge Transfer in Language Models with Entity-based Data Augmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Ikuya Yamada, Ryokan Ri","submitted_at":"2024-02-18T07:24:34Z","abstract_excerpt":"Adapting English-based large language models (LLMs) to other languages has become increasingly popular due to the efficiency and potential of cross-lingual transfer. However, existing language adaptation methods often overlook the benefits of cross-lingual supervision. In this study, we introduce LEIA, a language adaptation tuning method that utilizes Wikipedia entity names aligned across languages. This method involves augmenting the target language corpus with English entity names and training the model using left-to-right language modeling. We assess LEIA on diverse question answering datas"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.11485","kind":"arxiv","version":2},"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/2402.11485/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":"2402.11485","created_at":"2026-07-05T08:28:06.184598+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.11485v2","created_at":"2026-07-05T08:28:06.184598+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.11485","created_at":"2026-07-05T08:28:06.184598+00:00"},{"alias_kind":"pith_short_12","alias_value":"LKRO3PNAVWOY","created_at":"2026-07-05T08:28:06.184598+00:00"},{"alias_kind":"pith_short_16","alias_value":"LKRO3PNAVWOYMMEV","created_at":"2026-07-05T08:28:06.184598+00:00"},{"alias_kind":"pith_short_8","alias_value":"LKRO3PNA","created_at":"2026-07-05T08:28:06.184598+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.08090","citing_title":"Multilingual LLMs Inherently Reward In-Language Time-Sensitive Semantic Alignment for Low-Resource Languages","ref_index":35,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LKRO3PNAVWOYMMEV4OZI5RTT43","json":"https://pith.science/pith/LKRO3PNAVWOYMMEV4OZI5RTT43.json","graph_json":"https://pith.science/api/pith-number/LKRO3PNAVWOYMMEV4OZI5RTT43/graph.json","events_json":"https://pith.science/api/pith-number/LKRO3PNAVWOYMMEV4OZI5RTT43/events.json","paper":"https://pith.science/paper/LKRO3PNA"},"agent_actions":{"view_html":"https://pith.science/pith/LKRO3PNAVWOYMMEV4OZI5RTT43","download_json":"https://pith.science/pith/LKRO3PNAVWOYMMEV4OZI5RTT43.json","view_paper":"https://pith.science/paper/LKRO3PNA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.11485&json=true","fetch_graph":"https://pith.science/api/pith-number/LKRO3PNAVWOYMMEV4OZI5RTT43/graph.json","fetch_events":"https://pith.science/api/pith-number/LKRO3PNAVWOYMMEV4OZI5RTT43/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LKRO3PNAVWOYMMEV4OZI5RTT43/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LKRO3PNAVWOYMMEV4OZI5RTT43/action/storage_attestation","attest_author":"https://pith.science/pith/LKRO3PNAVWOYMMEV4OZI5RTT43/action/author_attestation","sign_citation":"https://pith.science/pith/LKRO3PNAVWOYMMEV4OZI5RTT43/action/citation_signature","submit_replication":"https://pith.science/pith/LKRO3PNAVWOYMMEV4OZI5RTT43/action/replication_record"}},"created_at":"2026-07-05T08:28:06.184598+00:00","updated_at":"2026-07-05T08:28:06.184598+00:00"}