{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:E6DJ6J6YYZO6MVWGCWUEMPIEAM","short_pith_number":"pith:E6DJ6J6Y","schema_version":"1.0","canonical_sha256":"27869f27d8c65de656c615a8463d040332cd3a70df5180d9541985dca8079efc","source":{"kind":"arxiv","id":"2309.08958","version":2},"attestation_state":"computed","paper":{"title":"Monolingual or Multilingual Instruction Tuning: Which Makes a Better Alpaca","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Andrey Kutuzov, Barry Haddow, Kenneth Heafield, Nikolay Bogoychev, Pinzhen Chen, Shaoxiong Ji","submitted_at":"2023-09-16T11:22:46Z","abstract_excerpt":"Foundational large language models (LLMs) can be instruction-tuned to perform open-domain question answering, facilitating applications like chat assistants. While such efforts are often carried out in a single language, we empirically analyze cost-efficient strategies for multilingual scenarios. Our study employs the Alpaca dataset and machine translations of it to form multilingual data, which is then used to tune LLMs through either low-rank adaptation or full-parameter training. Under a controlled computation budget, comparisons show that multilingual tuning is on par or better than tuning"},"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":"2309.08958","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-09-16T11:22:46Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"739c2b3366d2c7b3ae99ce3c9b5b511551e7b892cc7581d8014648cd0ec9ebbe","abstract_canon_sha256":"8a50d7afd2b88340a5982b05edf87b6c68b513148108ee0ba338b2c703ec9b63"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:39:30.356990Z","signature_b64":"JAx/e8+l45LIsPpDeaBJyO+bOsXW/Auvj60+wpi4Wi19v1/LbvQaj8Qm1W8lfLHfOCCxqXYca2MVtLKl6C73Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"27869f27d8c65de656c615a8463d040332cd3a70df5180d9541985dca8079efc","last_reissued_at":"2026-07-05T07:39:30.356481Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:39:30.356481Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Monolingual or Multilingual Instruction Tuning: Which Makes a Better Alpaca","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Andrey Kutuzov, Barry Haddow, Kenneth Heafield, Nikolay Bogoychev, Pinzhen Chen, Shaoxiong Ji","submitted_at":"2023-09-16T11:22:46Z","abstract_excerpt":"Foundational large language models (LLMs) can be instruction-tuned to perform open-domain question answering, facilitating applications like chat assistants. While such efforts are often carried out in a single language, we empirically analyze cost-efficient strategies for multilingual scenarios. Our study employs the Alpaca dataset and machine translations of it to form multilingual data, which is then used to tune LLMs through either low-rank adaptation or full-parameter training. Under a controlled computation budget, comparisons show that multilingual tuning is on par or better than tuning"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.08958","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/2309.08958/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":"2309.08958","created_at":"2026-07-05T07:39:30.356546+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.08958v2","created_at":"2026-07-05T07:39:30.356546+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.08958","created_at":"2026-07-05T07:39:30.356546+00:00"},{"alias_kind":"pith_short_12","alias_value":"E6DJ6J6YYZO6","created_at":"2026-07-05T07:39:30.356546+00:00"},{"alias_kind":"pith_short_16","alias_value":"E6DJ6J6YYZO6MVWG","created_at":"2026-07-05T07:39:30.356546+00:00"},{"alias_kind":"pith_short_8","alias_value":"E6DJ6J6Y","created_at":"2026-07-05T07:39:30.356546+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.09114","citing_title":"Preperiodic points, finiteness, and structures of semigroups of algebraic morphisms","ref_index":41,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/E6DJ6J6YYZO6MVWGCWUEMPIEAM","json":"https://pith.science/pith/E6DJ6J6YYZO6MVWGCWUEMPIEAM.json","graph_json":"https://pith.science/api/pith-number/E6DJ6J6YYZO6MVWGCWUEMPIEAM/graph.json","events_json":"https://pith.science/api/pith-number/E6DJ6J6YYZO6MVWGCWUEMPIEAM/events.json","paper":"https://pith.science/paper/E6DJ6J6Y"},"agent_actions":{"view_html":"https://pith.science/pith/E6DJ6J6YYZO6MVWGCWUEMPIEAM","download_json":"https://pith.science/pith/E6DJ6J6YYZO6MVWGCWUEMPIEAM.json","view_paper":"https://pith.science/paper/E6DJ6J6Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.08958&json=true","fetch_graph":"https://pith.science/api/pith-number/E6DJ6J6YYZO6MVWGCWUEMPIEAM/graph.json","fetch_events":"https://pith.science/api/pith-number/E6DJ6J6YYZO6MVWGCWUEMPIEAM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/E6DJ6J6YYZO6MVWGCWUEMPIEAM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/E6DJ6J6YYZO6MVWGCWUEMPIEAM/action/storage_attestation","attest_author":"https://pith.science/pith/E6DJ6J6YYZO6MVWGCWUEMPIEAM/action/author_attestation","sign_citation":"https://pith.science/pith/E6DJ6J6YYZO6MVWGCWUEMPIEAM/action/citation_signature","submit_replication":"https://pith.science/pith/E6DJ6J6YYZO6MVWGCWUEMPIEAM/action/replication_record"}},"created_at":"2026-07-05T07:39:30.356546+00:00","updated_at":"2026-07-05T07:39:30.356546+00:00"}