{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CQVXM2DWY4ZUU6O3IO3KEYIAM4","short_pith_number":"pith:CQVXM2DW","schema_version":"1.0","canonical_sha256":"142b766876c7334a79db43b6a26100671e50ee05a19616107992986fd515cfde","source":{"kind":"arxiv","id":"2406.16783","version":3},"attestation_state":"computed","paper":{"title":"M2Lingual: Enhancing Multilingual, Multi-Turn Instruction Alignment in Large Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Hoang Nguyen, Khyati Mahajan, Rishabh Maheshwary, Sathwik Tejaswi Madhusudhan, Vikas Yadav","submitted_at":"2024-06-24T16:45:13Z","abstract_excerpt":"Instruction finetuning (IFT) is critical for aligning Large Language Models (LLMs) to follow instructions. While many effective IFT datasets have been introduced recently, they predominantly focus on high-resource languages like English. To better align LLMs across a broad spectrum of languages and tasks, we propose a fully synthetic, novel taxonomy (Evol) guided Multilingual, Multi-turn instruction finetuning dataset, called M2Lingual. It is constructed by first selecting a diverse set of seed examples and then utilizing the proposed Evol taxonomy to convert these seeds into complex and chall"},"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":"2406.16783","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-24T16:45:13Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"a4bf0c8cf5f66efdf122a744d5c34e0f4ea8a278498ad400ecc2cc5321738b8a","abstract_canon_sha256":"f3f0c64a73dbabd802e823f7597b3c5749f7c5eaf55b009a517c8b415ed5684c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:23:20.457301Z","signature_b64":"xm6SbdghQoGEmy+G8Gyd8/Q9GvLbpcSLmZnwJryGTc9/hG13R6LYPuigBnnEr184mV/wfvDJ6QFCEXenSRcfCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"142b766876c7334a79db43b6a26100671e50ee05a19616107992986fd515cfde","last_reissued_at":"2026-07-05T10:23:20.456685Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:23:20.456685Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"M2Lingual: Enhancing Multilingual, Multi-Turn Instruction Alignment in Large Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Hoang Nguyen, Khyati Mahajan, Rishabh Maheshwary, Sathwik Tejaswi Madhusudhan, Vikas Yadav","submitted_at":"2024-06-24T16:45:13Z","abstract_excerpt":"Instruction finetuning (IFT) is critical for aligning Large Language Models (LLMs) to follow instructions. While many effective IFT datasets have been introduced recently, they predominantly focus on high-resource languages like English. To better align LLMs across a broad spectrum of languages and tasks, we propose a fully synthetic, novel taxonomy (Evol) guided Multilingual, Multi-turn instruction finetuning dataset, called M2Lingual. It is constructed by first selecting a diverse set of seed examples and then utilizing the proposed Evol taxonomy to convert these seeds into complex and chall"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.16783","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/2406.16783/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":"2406.16783","created_at":"2026-07-05T10:23:20.456769+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.16783v3","created_at":"2026-07-05T10:23:20.456769+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.16783","created_at":"2026-07-05T10:23:20.456769+00:00"},{"alias_kind":"pith_short_12","alias_value":"CQVXM2DWY4ZU","created_at":"2026-07-05T10:23:20.456769+00:00"},{"alias_kind":"pith_short_16","alias_value":"CQVXM2DWY4ZUU6O3","created_at":"2026-07-05T10:23:20.456769+00:00"},{"alias_kind":"pith_short_8","alias_value":"CQVXM2DW","created_at":"2026-07-05T10:23:20.456769+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.19996","citing_title":"ReSURE: Regularizing Supervision Unreliability for Multi-turn Dialogue Fine-tuning","ref_index":40,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CQVXM2DWY4ZUU6O3IO3KEYIAM4","json":"https://pith.science/pith/CQVXM2DWY4ZUU6O3IO3KEYIAM4.json","graph_json":"https://pith.science/api/pith-number/CQVXM2DWY4ZUU6O3IO3KEYIAM4/graph.json","events_json":"https://pith.science/api/pith-number/CQVXM2DWY4ZUU6O3IO3KEYIAM4/events.json","paper":"https://pith.science/paper/CQVXM2DW"},"agent_actions":{"view_html":"https://pith.science/pith/CQVXM2DWY4ZUU6O3IO3KEYIAM4","download_json":"https://pith.science/pith/CQVXM2DWY4ZUU6O3IO3KEYIAM4.json","view_paper":"https://pith.science/paper/CQVXM2DW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.16783&json=true","fetch_graph":"https://pith.science/api/pith-number/CQVXM2DWY4ZUU6O3IO3KEYIAM4/graph.json","fetch_events":"https://pith.science/api/pith-number/CQVXM2DWY4ZUU6O3IO3KEYIAM4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CQVXM2DWY4ZUU6O3IO3KEYIAM4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CQVXM2DWY4ZUU6O3IO3KEYIAM4/action/storage_attestation","attest_author":"https://pith.science/pith/CQVXM2DWY4ZUU6O3IO3KEYIAM4/action/author_attestation","sign_citation":"https://pith.science/pith/CQVXM2DWY4ZUU6O3IO3KEYIAM4/action/citation_signature","submit_replication":"https://pith.science/pith/CQVXM2DWY4ZUU6O3IO3KEYIAM4/action/replication_record"}},"created_at":"2026-07-05T10:23:20.456769+00:00","updated_at":"2026-07-05T10:23:20.456769+00:00"}