{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NZBLRWBEQQ4G7VKHNS45EPLJML","short_pith_number":"pith:NZBLRWBE","schema_version":"1.0","canonical_sha256":"6e42b8d82484386fd5476cb9d23d6962d840cf8285630764f34e7e979dfc2994","source":{"kind":"arxiv","id":"2410.04407","version":2},"attestation_state":"computed","paper":{"title":"Lens: Rethinking Multilingual Enhancement for Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bing Qin, Jiahe Guo, Ting Liu, Tongtong Wu, Wanxiang Che, Weixiang Zhao, Xingyu Sui, Yang Deng, Yanyan Zhao, Yulin Hu","submitted_at":"2024-10-06T08:51:30Z","abstract_excerpt":"As global demand for multilingual large language models (LLMs) grows, most LLMs still remain overly focused on English, leading to the limited access to advanced AI for non-English speakers. Current methods to enhance multilingual capabilities largely rely on data-driven post-training techniques, such as multilingual instruction tuning or continual pre-training. However, these approaches exhibit significant limitations, including high resource cost, exacerbation of off-target issue and catastrophic forgetting of central language abilities. To this end, we propose Lens, a novel approach that en"},"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":"2410.04407","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-06T08:51:30Z","cross_cats_sorted":[],"title_canon_sha256":"7cd06b724744a6a4e9a37b466d5d3988d7213cef586ac49d5848e6bb2b0d63cb","abstract_canon_sha256":"67cba0d2b1e729eddd79cda12c30d4b16b87e2ec9388b1351044f067f35540b4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:01.241781Z","signature_b64":"Ob+D0SRHgSmEN26vMt1H63sxb5AYsPPFUOFIk9uQYBrVHdigS+fpIChfY5YB+iSJy97c0eT+GnojjgmCSwFSCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6e42b8d82484386fd5476cb9d23d6962d840cf8285630764f34e7e979dfc2994","last_reissued_at":"2026-07-05T11:09:01.241252Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:01.241252Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Lens: Rethinking Multilingual Enhancement for Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bing Qin, Jiahe Guo, Ting Liu, Tongtong Wu, Wanxiang Che, Weixiang Zhao, Xingyu Sui, Yang Deng, Yanyan Zhao, Yulin Hu","submitted_at":"2024-10-06T08:51:30Z","abstract_excerpt":"As global demand for multilingual large language models (LLMs) grows, most LLMs still remain overly focused on English, leading to the limited access to advanced AI for non-English speakers. Current methods to enhance multilingual capabilities largely rely on data-driven post-training techniques, such as multilingual instruction tuning or continual pre-training. However, these approaches exhibit significant limitations, including high resource cost, exacerbation of off-target issue and catastrophic forgetting of central language abilities. To this end, we propose Lens, a novel approach that en"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.04407","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/2410.04407/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":"2410.04407","created_at":"2026-07-05T11:09:01.241327+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.04407v2","created_at":"2026-07-05T11:09:01.241327+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.04407","created_at":"2026-07-05T11:09:01.241327+00:00"},{"alias_kind":"pith_short_12","alias_value":"NZBLRWBEQQ4G","created_at":"2026-07-05T11:09:01.241327+00:00"},{"alias_kind":"pith_short_16","alias_value":"NZBLRWBEQQ4G7VKH","created_at":"2026-07-05T11:09:01.241327+00:00"},{"alias_kind":"pith_short_8","alias_value":"NZBLRWBE","created_at":"2026-07-05T11:09:01.241327+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.20720","citing_title":"COMPASS: COntinual Multilingual PEFT with Adaptive Semantic Sampling","ref_index":88,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NZBLRWBEQQ4G7VKHNS45EPLJML","json":"https://pith.science/pith/NZBLRWBEQQ4G7VKHNS45EPLJML.json","graph_json":"https://pith.science/api/pith-number/NZBLRWBEQQ4G7VKHNS45EPLJML/graph.json","events_json":"https://pith.science/api/pith-number/NZBLRWBEQQ4G7VKHNS45EPLJML/events.json","paper":"https://pith.science/paper/NZBLRWBE"},"agent_actions":{"view_html":"https://pith.science/pith/NZBLRWBEQQ4G7VKHNS45EPLJML","download_json":"https://pith.science/pith/NZBLRWBEQQ4G7VKHNS45EPLJML.json","view_paper":"https://pith.science/paper/NZBLRWBE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.04407&json=true","fetch_graph":"https://pith.science/api/pith-number/NZBLRWBEQQ4G7VKHNS45EPLJML/graph.json","fetch_events":"https://pith.science/api/pith-number/NZBLRWBEQQ4G7VKHNS45EPLJML/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NZBLRWBEQQ4G7VKHNS45EPLJML/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NZBLRWBEQQ4G7VKHNS45EPLJML/action/storage_attestation","attest_author":"https://pith.science/pith/NZBLRWBEQQ4G7VKHNS45EPLJML/action/author_attestation","sign_citation":"https://pith.science/pith/NZBLRWBEQQ4G7VKHNS45EPLJML/action/citation_signature","submit_replication":"https://pith.science/pith/NZBLRWBEQQ4G7VKHNS45EPLJML/action/replication_record"}},"created_at":"2026-07-05T11:09:01.241327+00:00","updated_at":"2026-07-05T11:09:01.241327+00:00"}