{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:7OYR75NTREFXDLQM2ULULRPYN4","short_pith_number":"pith:7OYR75NT","schema_version":"1.0","canonical_sha256":"fbb11ff5b3890b71ae0cd51745c5f86f1ad9b60e083382978078f0125f8040eb","source":{"kind":"arxiv","id":"2310.14819","version":1},"attestation_state":"computed","paper":{"title":"Analyzing Multilingual Competency of LLMs in Multi-Turn Instruction Following: A Case Study of Arabic","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Majd Hawasly, Sabri Boughorbel","submitted_at":"2023-10-23T11:40:04Z","abstract_excerpt":"While significant progress has been made in benchmarking Large Language Models (LLMs) across various tasks, there is a lack of comprehensive evaluation of their abilities in responding to multi-turn instructions in less-commonly tested languages like Arabic. Our paper offers a detailed examination of the proficiency of open LLMs in such scenarios in Arabic. Utilizing a customized Arabic translation of the MT-Bench benchmark suite, we employ GPT-4 as a uniform evaluator for both English and Arabic queries to assess and compare the performance of the LLMs on various open-ended tasks. Our finding"},"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":"2310.14819","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-23T11:40:04Z","cross_cats_sorted":[],"title_canon_sha256":"54e3f4bb6416135f725047ac8f9203eefba37e3f21885fe26bfca99d57837a18","abstract_canon_sha256":"7739c7c9412a42bc0984ddc8abb9a71fdc8e61011b7e1185f40c4f55ba07e870"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:04:02.542641Z","signature_b64":"6oMsuv9Ed3ifLba6AXWxFzgYjOD0UAnrM7HiCH74GOmmsDl2NiYVLfN8bGw7eAT2CMRY5zSNQlcgVYy/pYj9Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fbb11ff5b3890b71ae0cd51745c5f86f1ad9b60e083382978078f0125f8040eb","last_reissued_at":"2026-07-05T07:04:02.542074Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:04:02.542074Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Analyzing Multilingual Competency of LLMs in Multi-Turn Instruction Following: A Case Study of Arabic","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Majd Hawasly, Sabri Boughorbel","submitted_at":"2023-10-23T11:40:04Z","abstract_excerpt":"While significant progress has been made in benchmarking Large Language Models (LLMs) across various tasks, there is a lack of comprehensive evaluation of their abilities in responding to multi-turn instructions in less-commonly tested languages like Arabic. Our paper offers a detailed examination of the proficiency of open LLMs in such scenarios in Arabic. Utilizing a customized Arabic translation of the MT-Bench benchmark suite, we employ GPT-4 as a uniform evaluator for both English and Arabic queries to assess and compare the performance of the LLMs on various open-ended tasks. Our finding"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.14819","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/2310.14819/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":"2310.14819","created_at":"2026-07-05T07:04:02.542132+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.14819v1","created_at":"2026-07-05T07:04:02.542132+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.14819","created_at":"2026-07-05T07:04:02.542132+00:00"},{"alias_kind":"pith_short_12","alias_value":"7OYR75NTREFX","created_at":"2026-07-05T07:04:02.542132+00:00"},{"alias_kind":"pith_short_16","alias_value":"7OYR75NTREFXDLQM","created_at":"2026-07-05T07:04:02.542132+00:00"},{"alias_kind":"pith_short_8","alias_value":"7OYR75NT","created_at":"2026-07-05T07:04:02.542132+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.19699","citing_title":"Towards Inclusive NLP: Assessing Compressed Multilingual Transformers across Diverse Language Benchmarks","ref_index":5,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7OYR75NTREFXDLQM2ULULRPYN4","json":"https://pith.science/pith/7OYR75NTREFXDLQM2ULULRPYN4.json","graph_json":"https://pith.science/api/pith-number/7OYR75NTREFXDLQM2ULULRPYN4/graph.json","events_json":"https://pith.science/api/pith-number/7OYR75NTREFXDLQM2ULULRPYN4/events.json","paper":"https://pith.science/paper/7OYR75NT"},"agent_actions":{"view_html":"https://pith.science/pith/7OYR75NTREFXDLQM2ULULRPYN4","download_json":"https://pith.science/pith/7OYR75NTREFXDLQM2ULULRPYN4.json","view_paper":"https://pith.science/paper/7OYR75NT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.14819&json=true","fetch_graph":"https://pith.science/api/pith-number/7OYR75NTREFXDLQM2ULULRPYN4/graph.json","fetch_events":"https://pith.science/api/pith-number/7OYR75NTREFXDLQM2ULULRPYN4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7OYR75NTREFXDLQM2ULULRPYN4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7OYR75NTREFXDLQM2ULULRPYN4/action/storage_attestation","attest_author":"https://pith.science/pith/7OYR75NTREFXDLQM2ULULRPYN4/action/author_attestation","sign_citation":"https://pith.science/pith/7OYR75NTREFXDLQM2ULULRPYN4/action/citation_signature","submit_replication":"https://pith.science/pith/7OYR75NTREFXDLQM2ULULRPYN4/action/replication_record"}},"created_at":"2026-07-05T07:04:02.542132+00:00","updated_at":"2026-07-05T07:04:02.542132+00:00"}