{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:U6Y2KTBZMHFJD6NNR55QY2SCRT","short_pith_number":"pith:U6Y2KTBZ","schema_version":"1.0","canonical_sha256":"a7b1a54c3961ca91f9ad8f7b0c6a428cc56f5bbacbcddd55a782a51f67c141be","source":{"kind":"arxiv","id":"2306.11372","version":2},"attestation_state":"computed","paper":{"title":"Democratizing LLMs for Low-Resource Languages by Leveraging their English Dominant Abilities with Linguistically-Diverse Prompts","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Lidong Bing, Shafiq Joty, Sharifah Mahani Aljunied, Xuan-Phi Nguyen","submitted_at":"2023-06-20T08:27:47Z","abstract_excerpt":"Large language models (LLMs) are known to effectively perform tasks by simply observing few exemplars. However, in low-resource languages, obtaining such hand-picked exemplars can still be challenging, where unsupervised techniques may be necessary. Moreover, competent generative capabilities of LLMs are observed only in high-resource languages, while their performances among under-represented languages fall behind due to pre-training data imbalance. To elicit LLMs' ability onto low-resource languages without any supervised data, we propose to assemble synthetic exemplars from a diverse set of"},"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":"2306.11372","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-20T08:27:47Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"cfec62aec815b2d18957b92b1731033b0925111b2883708f4f59f91639cb302c","abstract_canon_sha256":"350b022d924877fe08c44d8ef531449a856f56cbf5a6349503556e181cd71182"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:46:05.938458Z","signature_b64":"Asj+E4sscXIOOd7dCdK5HrhIn7D49gLuxoUPQqwx+MD36zRBwixJBQn7N+pXHNV8JEVFg0O8mObVPJ3RAVbeCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a7b1a54c3961ca91f9ad8f7b0c6a428cc56f5bbacbcddd55a782a51f67c141be","last_reissued_at":"2026-07-05T08:46:05.937986Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:46:05.937986Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Democratizing LLMs for Low-Resource Languages by Leveraging their English Dominant Abilities with Linguistically-Diverse Prompts","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Lidong Bing, Shafiq Joty, Sharifah Mahani Aljunied, Xuan-Phi Nguyen","submitted_at":"2023-06-20T08:27:47Z","abstract_excerpt":"Large language models (LLMs) are known to effectively perform tasks by simply observing few exemplars. However, in low-resource languages, obtaining such hand-picked exemplars can still be challenging, where unsupervised techniques may be necessary. Moreover, competent generative capabilities of LLMs are observed only in high-resource languages, while their performances among under-represented languages fall behind due to pre-training data imbalance. To elicit LLMs' ability onto low-resource languages without any supervised data, we propose to assemble synthetic exemplars from a diverse set of"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.11372","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/2306.11372/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":"2306.11372","created_at":"2026-07-05T08:46:05.938041+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.11372v2","created_at":"2026-07-05T08:46:05.938041+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.11372","created_at":"2026-07-05T08:46:05.938041+00:00"},{"alias_kind":"pith_short_12","alias_value":"U6Y2KTBZMHFJ","created_at":"2026-07-05T08:46:05.938041+00:00"},{"alias_kind":"pith_short_16","alias_value":"U6Y2KTBZMHFJD6NN","created_at":"2026-07-05T08:46:05.938041+00:00"},{"alias_kind":"pith_short_8","alias_value":"U6Y2KTBZ","created_at":"2026-07-05T08:46:05.938041+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2601.13262","citing_title":"CURE-Med: Curriculum-Informed Reinforcement Learning for Multilingual Medical Reasoning","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/U6Y2KTBZMHFJD6NNR55QY2SCRT","json":"https://pith.science/pith/U6Y2KTBZMHFJD6NNR55QY2SCRT.json","graph_json":"https://pith.science/api/pith-number/U6Y2KTBZMHFJD6NNR55QY2SCRT/graph.json","events_json":"https://pith.science/api/pith-number/U6Y2KTBZMHFJD6NNR55QY2SCRT/events.json","paper":"https://pith.science/paper/U6Y2KTBZ"},"agent_actions":{"view_html":"https://pith.science/pith/U6Y2KTBZMHFJD6NNR55QY2SCRT","download_json":"https://pith.science/pith/U6Y2KTBZMHFJD6NNR55QY2SCRT.json","view_paper":"https://pith.science/paper/U6Y2KTBZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.11372&json=true","fetch_graph":"https://pith.science/api/pith-number/U6Y2KTBZMHFJD6NNR55QY2SCRT/graph.json","fetch_events":"https://pith.science/api/pith-number/U6Y2KTBZMHFJD6NNR55QY2SCRT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U6Y2KTBZMHFJD6NNR55QY2SCRT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U6Y2KTBZMHFJD6NNR55QY2SCRT/action/storage_attestation","attest_author":"https://pith.science/pith/U6Y2KTBZMHFJD6NNR55QY2SCRT/action/author_attestation","sign_citation":"https://pith.science/pith/U6Y2KTBZMHFJD6NNR55QY2SCRT/action/citation_signature","submit_replication":"https://pith.science/pith/U6Y2KTBZMHFJD6NNR55QY2SCRT/action/replication_record"}},"created_at":"2026-07-05T08:46:05.938041+00:00","updated_at":"2026-07-05T08:46:05.938041+00:00"}