{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XE5T2XSNFE3ZJRIGJPK3MZUM6N","short_pith_number":"pith:XE5T2XSN","schema_version":"1.0","canonical_sha256":"b93b3d5e4d293794c5064bd5b6668cf36077b2dd56d068180522b036097d332d","source":{"kind":"arxiv","id":"2407.09879","version":4},"attestation_state":"computed","paper":{"title":"sPhinX: Sample Efficient Multilingual Instruction Fine-Tuning Through N-shot Guided Prompting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ahmed Awadallah, Arindam Mitra, Barun Patra, Hardik Hansrajbhai Chauhan, Kriti Aggarwal, Kumar Tanmay, Luciano Del Corro, Monojit Choudhary, Sanchit Ahuja, Sunayana Sitaram, Tejas Indulal Dhamecha, Vishrav Chaudhary","submitted_at":"2024-07-13T13:03:45Z","abstract_excerpt":"Despite the remarkable success of large language models (LLMs) in English, a significant performance gap remains in non-English languages. To address this, we introduce a novel approach for strategically constructing a multilingual synthetic instruction tuning dataset, sPhinX. Unlike prior methods that directly translate fixed instruction-response pairs, sPhinX enhances diversity by selectively augmenting English instruction-response pairs with multilingual translations. Additionally, we propose LANGIT, a novel N-shot guided fine-tuning strategy, which further enhances model performance by inc"},"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":"2407.09879","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-13T13:03:45Z","cross_cats_sorted":[],"title_canon_sha256":"6a790bdc75e55d64c42d8656196138bfa1e166b7bdf4647d2a755fd52494dbcc","abstract_canon_sha256":"c051aaf219ad27075e4034f140a5990c68571d35d5431574053d4f1170aa10a2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:23:49.470237Z","signature_b64":"SW3pHvS9yL1daP6NsDgZvV84hxssTOKL6Btrd//WSXadRlgCQkvMOfx5TXSDsJxtH0T1MFNh4/irNgaYi5xOBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b93b3d5e4d293794c5064bd5b6668cf36077b2dd56d068180522b036097d332d","last_reissued_at":"2026-07-05T11:23:49.469809Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:23:49.469809Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"sPhinX: Sample Efficient Multilingual Instruction Fine-Tuning Through N-shot Guided Prompting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ahmed Awadallah, Arindam Mitra, Barun Patra, Hardik Hansrajbhai Chauhan, Kriti Aggarwal, Kumar Tanmay, Luciano Del Corro, Monojit Choudhary, Sanchit Ahuja, Sunayana Sitaram, Tejas Indulal Dhamecha, Vishrav Chaudhary","submitted_at":"2024-07-13T13:03:45Z","abstract_excerpt":"Despite the remarkable success of large language models (LLMs) in English, a significant performance gap remains in non-English languages. To address this, we introduce a novel approach for strategically constructing a multilingual synthetic instruction tuning dataset, sPhinX. Unlike prior methods that directly translate fixed instruction-response pairs, sPhinX enhances diversity by selectively augmenting English instruction-response pairs with multilingual translations. Additionally, we propose LANGIT, a novel N-shot guided fine-tuning strategy, which further enhances model performance by inc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.09879","kind":"arxiv","version":4},"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/2407.09879/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":"2407.09879","created_at":"2026-07-05T11:23:49.469867+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.09879v4","created_at":"2026-07-05T11:23:49.469867+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.09879","created_at":"2026-07-05T11:23:49.469867+00:00"},{"alias_kind":"pith_short_12","alias_value":"XE5T2XSNFE3Z","created_at":"2026-07-05T11:23:49.469867+00:00"},{"alias_kind":"pith_short_16","alias_value":"XE5T2XSNFE3ZJRIG","created_at":"2026-07-05T11:23:49.469867+00:00"},{"alias_kind":"pith_short_8","alias_value":"XE5T2XSN","created_at":"2026-07-05T11:23:49.469867+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.09890","citing_title":"The Emergence of Abstract Thought in Large Language Models Beyond Any Language","ref_index":4,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XE5T2XSNFE3ZJRIGJPK3MZUM6N","json":"https://pith.science/pith/XE5T2XSNFE3ZJRIGJPK3MZUM6N.json","graph_json":"https://pith.science/api/pith-number/XE5T2XSNFE3ZJRIGJPK3MZUM6N/graph.json","events_json":"https://pith.science/api/pith-number/XE5T2XSNFE3ZJRIGJPK3MZUM6N/events.json","paper":"https://pith.science/paper/XE5T2XSN"},"agent_actions":{"view_html":"https://pith.science/pith/XE5T2XSNFE3ZJRIGJPK3MZUM6N","download_json":"https://pith.science/pith/XE5T2XSNFE3ZJRIGJPK3MZUM6N.json","view_paper":"https://pith.science/paper/XE5T2XSN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.09879&json=true","fetch_graph":"https://pith.science/api/pith-number/XE5T2XSNFE3ZJRIGJPK3MZUM6N/graph.json","fetch_events":"https://pith.science/api/pith-number/XE5T2XSNFE3ZJRIGJPK3MZUM6N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XE5T2XSNFE3ZJRIGJPK3MZUM6N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XE5T2XSNFE3ZJRIGJPK3MZUM6N/action/storage_attestation","attest_author":"https://pith.science/pith/XE5T2XSNFE3ZJRIGJPK3MZUM6N/action/author_attestation","sign_citation":"https://pith.science/pith/XE5T2XSNFE3ZJRIGJPK3MZUM6N/action/citation_signature","submit_replication":"https://pith.science/pith/XE5T2XSNFE3ZJRIGJPK3MZUM6N/action/replication_record"}},"created_at":"2026-07-05T11:23:49.469867+00:00","updated_at":"2026-07-05T11:23:49.469867+00:00"}