{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:75AVZUM6ZYUEBXL2LERIILQI4E","short_pith_number":"pith:75AVZUM6","schema_version":"1.0","canonical_sha256":"ff415cd19ece2840dd7a5922842e08e1175ae04fdbe057998d77d5a9886cde75","source":{"kind":"arxiv","id":"2407.01853","version":1},"attestation_state":"computed","paper":{"title":"Improving Multilingual Instruction Finetuning via Linguistically Natural and Diverse Datasets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Chenguang Zhu, Kaiqiang Song, Lingxiao Zhao, Ravi Agrawal, Sathish Reddy Indurthi, Shamil Chollampatt, Wenxuan Zhou","submitted_at":"2024-07-01T23:47:09Z","abstract_excerpt":"Advancements in Large Language Models (LLMs) have significantly enhanced instruction-following capabilities. However, most Instruction Fine-Tuning (IFT) datasets are predominantly in English, limiting model performance in other languages. Traditional methods for creating multilingual IFT datasets such as translating existing English IFT datasets or converting existing NLP datasets into IFT datasets by templating, struggle to capture linguistic nuances and ensure prompt (instruction) diversity. To address this issue, we propose a novel method for collecting multilingual IFT datasets that preser"},"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":"2407.01853","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-01T23:47:09Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"0a4633e673d0d423d73c1b5df5b76e9211397c528367bdc1cd3c4d44d0171cb2","abstract_canon_sha256":"4e1d1c0af7311a3b11a0644741aad525a4e700279fbf516d7362fab474a679e9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:39:06.175432Z","signature_b64":"+fEFmTKSgeDWMQwJN9jnNqlFtwUr4ZmWukvYiYoQWCO+SM8N2ACi/CMzOV3ndVGsFXiACaqGWCget/4MCI9kCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ff415cd19ece2840dd7a5922842e08e1175ae04fdbe057998d77d5a9886cde75","last_reissued_at":"2026-07-05T08:39:06.174891Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:39:06.174891Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Multilingual Instruction Finetuning via Linguistically Natural and Diverse Datasets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Chenguang Zhu, Kaiqiang Song, Lingxiao Zhao, Ravi Agrawal, Sathish Reddy Indurthi, Shamil Chollampatt, Wenxuan Zhou","submitted_at":"2024-07-01T23:47:09Z","abstract_excerpt":"Advancements in Large Language Models (LLMs) have significantly enhanced instruction-following capabilities. However, most Instruction Fine-Tuning (IFT) datasets are predominantly in English, limiting model performance in other languages. Traditional methods for creating multilingual IFT datasets such as translating existing English IFT datasets or converting existing NLP datasets into IFT datasets by templating, struggle to capture linguistic nuances and ensure prompt (instruction) diversity. To address this issue, we propose a novel method for collecting multilingual IFT datasets that preser"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.01853","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/2407.01853/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":"2407.01853","created_at":"2026-07-05T08:39:06.174949+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.01853v1","created_at":"2026-07-05T08:39:06.174949+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.01853","created_at":"2026-07-05T08:39:06.174949+00:00"},{"alias_kind":"pith_short_12","alias_value":"75AVZUM6ZYUE","created_at":"2026-07-05T08:39:06.174949+00:00"},{"alias_kind":"pith_short_16","alias_value":"75AVZUM6ZYUEBXL2","created_at":"2026-07-05T08:39:06.174949+00:00"},{"alias_kind":"pith_short_8","alias_value":"75AVZUM6","created_at":"2026-07-05T08:39:06.174949+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":27,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/75AVZUM6ZYUEBXL2LERIILQI4E","json":"https://pith.science/pith/75AVZUM6ZYUEBXL2LERIILQI4E.json","graph_json":"https://pith.science/api/pith-number/75AVZUM6ZYUEBXL2LERIILQI4E/graph.json","events_json":"https://pith.science/api/pith-number/75AVZUM6ZYUEBXL2LERIILQI4E/events.json","paper":"https://pith.science/paper/75AVZUM6"},"agent_actions":{"view_html":"https://pith.science/pith/75AVZUM6ZYUEBXL2LERIILQI4E","download_json":"https://pith.science/pith/75AVZUM6ZYUEBXL2LERIILQI4E.json","view_paper":"https://pith.science/paper/75AVZUM6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.01853&json=true","fetch_graph":"https://pith.science/api/pith-number/75AVZUM6ZYUEBXL2LERIILQI4E/graph.json","fetch_events":"https://pith.science/api/pith-number/75AVZUM6ZYUEBXL2LERIILQI4E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/75AVZUM6ZYUEBXL2LERIILQI4E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/75AVZUM6ZYUEBXL2LERIILQI4E/action/storage_attestation","attest_author":"https://pith.science/pith/75AVZUM6ZYUEBXL2LERIILQI4E/action/author_attestation","sign_citation":"https://pith.science/pith/75AVZUM6ZYUEBXL2LERIILQI4E/action/citation_signature","submit_replication":"https://pith.science/pith/75AVZUM6ZYUEBXL2LERIILQI4E/action/replication_record"}},"created_at":"2026-07-05T08:39:06.174949+00:00","updated_at":"2026-07-05T08:39:06.174949+00:00"}