{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:27DMIGCRN2AG4AHCOO7UL3ZRVJ","short_pith_number":"pith:27DMIGCR","schema_version":"1.0","canonical_sha256":"d7c6c418516e806e00e273bf45ef31aa7d7240bc7f6aebc4fc56070e47500441","source":{"kind":"arxiv","id":"2510.14466","version":3},"attestation_state":"computed","paper":{"title":"Toward Robust Multilingual Adaptation of LLMs for Low-Resource Languages","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Biqing Huang, Haipeng Zhang, Haolin Li, Lijie Wen, Mang Li, Yaohua Wang, Yu Zhang","submitted_at":"2025-10-16T09:08:24Z","abstract_excerpt":"Large language models (LLMs) continue to struggle with low-resource languages, primarily due to limited training data, translation noise, and unstable cross-lingual alignment. To address these challenges, we propose LiRA (Linguistic Robust Anchoring for LLMs)-a plug-and-play framework that requires only lightweight fine-tuning on top of existing pretrained backbones. LiRA jointly optimizes representation stability and cross-lingual semantic consistency by combining two key components: Arca (Anchored Representation Composition Architecture), which aligns low-resource inputs to a shared English "},"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":"2510.14466","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-10-16T09:08:24Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"534673e897549959b8eab0ccf98ffa356790404d0fa6f89fc17a5d594bbf7325","abstract_canon_sha256":"52118a62d7732815091697d0fdd653e7319b34dfcd364516008d464f7f4ec8a5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:04:14.852270Z","signature_b64":"23CXLOz09rKqK5RBDvRXVYTLdMqqdz9hlQw7UNipoZi4Th2HUHZW0sxHbPCZ2mW9tjtr4txtBKTuiHbcQ9ZYBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d7c6c418516e806e00e273bf45ef31aa7d7240bc7f6aebc4fc56070e47500441","last_reissued_at":"2026-05-20T00:04:14.851686Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:04:14.851686Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Toward Robust Multilingual Adaptation of LLMs for Low-Resource Languages","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Biqing Huang, Haipeng Zhang, Haolin Li, Lijie Wen, Mang Li, Yaohua Wang, Yu Zhang","submitted_at":"2025-10-16T09:08:24Z","abstract_excerpt":"Large language models (LLMs) continue to struggle with low-resource languages, primarily due to limited training data, translation noise, and unstable cross-lingual alignment. To address these challenges, we propose LiRA (Linguistic Robust Anchoring for LLMs)-a plug-and-play framework that requires only lightweight fine-tuning on top of existing pretrained backbones. LiRA jointly optimizes representation stability and cross-lingual semantic consistency by combining two key components: Arca (Anchored Representation Composition Architecture), which aligns low-resource inputs to a shared English "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.14466","kind":"arxiv","version":3},"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/2510.14466/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":"2510.14466","created_at":"2026-05-20T00:04:14.851772+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.14466v3","created_at":"2026-05-20T00:04:14.851772+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.14466","created_at":"2026-05-20T00:04:14.851772+00:00"},{"alias_kind":"pith_short_12","alias_value":"27DMIGCRN2AG","created_at":"2026-05-20T00:04:14.851772+00:00"},{"alias_kind":"pith_short_16","alias_value":"27DMIGCRN2AG4AHC","created_at":"2026-05-20T00:04:14.851772+00:00"},{"alias_kind":"pith_short_8","alias_value":"27DMIGCR","created_at":"2026-05-20T00:04:14.851772+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/27DMIGCRN2AG4AHCOO7UL3ZRVJ","json":"https://pith.science/pith/27DMIGCRN2AG4AHCOO7UL3ZRVJ.json","graph_json":"https://pith.science/api/pith-number/27DMIGCRN2AG4AHCOO7UL3ZRVJ/graph.json","events_json":"https://pith.science/api/pith-number/27DMIGCRN2AG4AHCOO7UL3ZRVJ/events.json","paper":"https://pith.science/paper/27DMIGCR"},"agent_actions":{"view_html":"https://pith.science/pith/27DMIGCRN2AG4AHCOO7UL3ZRVJ","download_json":"https://pith.science/pith/27DMIGCRN2AG4AHCOO7UL3ZRVJ.json","view_paper":"https://pith.science/paper/27DMIGCR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.14466&json=true","fetch_graph":"https://pith.science/api/pith-number/27DMIGCRN2AG4AHCOO7UL3ZRVJ/graph.json","fetch_events":"https://pith.science/api/pith-number/27DMIGCRN2AG4AHCOO7UL3ZRVJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/27DMIGCRN2AG4AHCOO7UL3ZRVJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/27DMIGCRN2AG4AHCOO7UL3ZRVJ/action/storage_attestation","attest_author":"https://pith.science/pith/27DMIGCRN2AG4AHCOO7UL3ZRVJ/action/author_attestation","sign_citation":"https://pith.science/pith/27DMIGCRN2AG4AHCOO7UL3ZRVJ/action/citation_signature","submit_replication":"https://pith.science/pith/27DMIGCRN2AG4AHCOO7UL3ZRVJ/action/replication_record"}},"created_at":"2026-05-20T00:04:14.851772+00:00","updated_at":"2026-05-20T00:04:14.851772+00:00"}