{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MEWYLTWHESDWLYGF6WNM2NDABG","short_pith_number":"pith:MEWYLTWH","schema_version":"1.0","canonical_sha256":"612d85cec7248765e0c5f59acd346009bf2874a3ac43ad609ea9b7a34b2c6abc","source":{"kind":"arxiv","id":"2505.14297","version":1},"attestation_state":"computed","paper":{"title":"Cross-Lingual Optimization for Language Transfer in Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Heuiseok Lim, Hyeonseok Moon, Jungseob Lee, Seongtae Hong","submitted_at":"2025-05-20T12:45:09Z","abstract_excerpt":"Adapting large language models to other languages typically employs supervised fine-tuning (SFT) as a standard approach. However, it often suffers from an overemphasis on English performance, a phenomenon that is especially pronounced in data-constrained environments. To overcome these challenges, we propose \\textbf{Cross-Lingual Optimization (CLO)} that efficiently transfers an English-centric LLM to a target language while preserving its English capabilities. CLO utilizes publicly available English SFT data and a translation model to enable cross-lingual transfer. We conduct experiments usin"},"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":"2505.14297","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-20T12:45:09Z","cross_cats_sorted":[],"title_canon_sha256":"6c1b4a87a93ae9c40d60904d78c82820e2d9ee11c90961919da52fa5e4a6ec5a","abstract_canon_sha256":"89bca8e757aa61856b180866bacdd9f704fd79058bf3364ae51007edf26c6b03"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:05:59.228458Z","signature_b64":"2TKOKRxUdr/PBSo1iD0Am837NV6NRBLaJkAspRquhWRTjRpYE1uwiAy+FEPWNS+oi50eSDhaVVkW4vNQwN3cBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"612d85cec7248765e0c5f59acd346009bf2874a3ac43ad609ea9b7a34b2c6abc","last_reissued_at":"2026-07-05T11:05:59.228004Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:05:59.228004Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cross-Lingual Optimization for Language Transfer in Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Heuiseok Lim, Hyeonseok Moon, Jungseob Lee, Seongtae Hong","submitted_at":"2025-05-20T12:45:09Z","abstract_excerpt":"Adapting large language models to other languages typically employs supervised fine-tuning (SFT) as a standard approach. However, it often suffers from an overemphasis on English performance, a phenomenon that is especially pronounced in data-constrained environments. To overcome these challenges, we propose \\textbf{Cross-Lingual Optimization (CLO)} that efficiently transfers an English-centric LLM to a target language while preserving its English capabilities. CLO utilizes publicly available English SFT data and a translation model to enable cross-lingual transfer. We conduct experiments usin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.14297","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/2505.14297/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":"2505.14297","created_at":"2026-07-05T11:05:59.228061+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.14297v1","created_at":"2026-07-05T11:05:59.228061+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.14297","created_at":"2026-07-05T11:05:59.228061+00:00"},{"alias_kind":"pith_short_12","alias_value":"MEWYLTWHESDW","created_at":"2026-07-05T11:05:59.228061+00:00"},{"alias_kind":"pith_short_16","alias_value":"MEWYLTWHESDWLYGF","created_at":"2026-07-05T11:05:59.228061+00:00"},{"alias_kind":"pith_short_8","alias_value":"MEWYLTWH","created_at":"2026-07-05T11:05:59.228061+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.06586","citing_title":"Improving Cross-Lingual Factual Recall via Consistency-Driven Reinforcement Learning","ref_index":42,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MEWYLTWHESDWLYGF6WNM2NDABG","json":"https://pith.science/pith/MEWYLTWHESDWLYGF6WNM2NDABG.json","graph_json":"https://pith.science/api/pith-number/MEWYLTWHESDWLYGF6WNM2NDABG/graph.json","events_json":"https://pith.science/api/pith-number/MEWYLTWHESDWLYGF6WNM2NDABG/events.json","paper":"https://pith.science/paper/MEWYLTWH"},"agent_actions":{"view_html":"https://pith.science/pith/MEWYLTWHESDWLYGF6WNM2NDABG","download_json":"https://pith.science/pith/MEWYLTWHESDWLYGF6WNM2NDABG.json","view_paper":"https://pith.science/paper/MEWYLTWH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.14297&json=true","fetch_graph":"https://pith.science/api/pith-number/MEWYLTWHESDWLYGF6WNM2NDABG/graph.json","fetch_events":"https://pith.science/api/pith-number/MEWYLTWHESDWLYGF6WNM2NDABG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MEWYLTWHESDWLYGF6WNM2NDABG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MEWYLTWHESDWLYGF6WNM2NDABG/action/storage_attestation","attest_author":"https://pith.science/pith/MEWYLTWHESDWLYGF6WNM2NDABG/action/author_attestation","sign_citation":"https://pith.science/pith/MEWYLTWHESDWLYGF6WNM2NDABG/action/citation_signature","submit_replication":"https://pith.science/pith/MEWYLTWHESDWLYGF6WNM2NDABG/action/replication_record"}},"created_at":"2026-07-05T11:05:59.228061+00:00","updated_at":"2026-07-05T11:05:59.228061+00:00"}