{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WMTV52VH6FXNAXGRQQ2NE4DUZJ","short_pith_number":"pith:WMTV52VH","schema_version":"1.0","canonical_sha256":"b3275eeaa7f16ed05cd18434d27074ca4aa21b6846489afd744aca8b4183ec6c","source":{"kind":"arxiv","id":"2409.13897","version":1},"attestation_state":"computed","paper":{"title":"LLM for Everyone: Representing the Underrepresented in Large Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Samuel Cahyawijaya","submitted_at":"2024-09-20T20:53:22Z","abstract_excerpt":"Natural language processing (NLP) has witnessed a profound impact of large language models (LLMs) that excel in a multitude of tasks. However, the limitation of LLMs in multilingual settings, particularly in underrepresented languages, remains a significant hurdle. This thesis aims to bridge the gap in NLP research and development by focusing on underrepresented languages. A comprehensive evaluation of LLMs is conducted to assess their capabilities in these languages, revealing the challenges of multilingual and multicultural generalization. Addressing the multilingual generalization gap, this"},"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":"2409.13897","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-20T20:53:22Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9b6cb49df7c02fbc6123fe7df59190078171d16e03f9204b03a81c447b31dc57","abstract_canon_sha256":"dce9f06f5c80eba6cdb8ce33ff66993f75b2dff4742e1777fc63585d95cd920f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:10:08.388941Z","signature_b64":"+RBHuRdu7Na2bt83/pBsWW3yTn7AoYWfKpYPJJEf6VU7r69rik4h7gUcQj4xYTYBidP7riDJYFo2aG4mV1BkBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b3275eeaa7f16ed05cd18434d27074ca4aa21b6846489afd744aca8b4183ec6c","last_reissued_at":"2026-07-05T09:10:08.388604Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:10:08.388604Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLM for Everyone: Representing the Underrepresented in Large Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Samuel Cahyawijaya","submitted_at":"2024-09-20T20:53:22Z","abstract_excerpt":"Natural language processing (NLP) has witnessed a profound impact of large language models (LLMs) that excel in a multitude of tasks. However, the limitation of LLMs in multilingual settings, particularly in underrepresented languages, remains a significant hurdle. This thesis aims to bridge the gap in NLP research and development by focusing on underrepresented languages. A comprehensive evaluation of LLMs is conducted to assess their capabilities in these languages, revealing the challenges of multilingual and multicultural generalization. Addressing the multilingual generalization gap, this"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.13897","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/2409.13897/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":"2409.13897","created_at":"2026-07-05T09:10:08.388659+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.13897v1","created_at":"2026-07-05T09:10:08.388659+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.13897","created_at":"2026-07-05T09:10:08.388659+00:00"},{"alias_kind":"pith_short_12","alias_value":"WMTV52VH6FXN","created_at":"2026-07-05T09:10:08.388659+00:00"},{"alias_kind":"pith_short_16","alias_value":"WMTV52VH6FXNAXGR","created_at":"2026-07-05T09:10:08.388659+00:00"},{"alias_kind":"pith_short_8","alias_value":"WMTV52VH","created_at":"2026-07-05T09:10:08.388659+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.11490","citing_title":"Anthropogenic Regional Adaptation in Multimodal Vision-Language Model","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WMTV52VH6FXNAXGRQQ2NE4DUZJ","json":"https://pith.science/pith/WMTV52VH6FXNAXGRQQ2NE4DUZJ.json","graph_json":"https://pith.science/api/pith-number/WMTV52VH6FXNAXGRQQ2NE4DUZJ/graph.json","events_json":"https://pith.science/api/pith-number/WMTV52VH6FXNAXGRQQ2NE4DUZJ/events.json","paper":"https://pith.science/paper/WMTV52VH"},"agent_actions":{"view_html":"https://pith.science/pith/WMTV52VH6FXNAXGRQQ2NE4DUZJ","download_json":"https://pith.science/pith/WMTV52VH6FXNAXGRQQ2NE4DUZJ.json","view_paper":"https://pith.science/paper/WMTV52VH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.13897&json=true","fetch_graph":"https://pith.science/api/pith-number/WMTV52VH6FXNAXGRQQ2NE4DUZJ/graph.json","fetch_events":"https://pith.science/api/pith-number/WMTV52VH6FXNAXGRQQ2NE4DUZJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WMTV52VH6FXNAXGRQQ2NE4DUZJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WMTV52VH6FXNAXGRQQ2NE4DUZJ/action/storage_attestation","attest_author":"https://pith.science/pith/WMTV52VH6FXNAXGRQQ2NE4DUZJ/action/author_attestation","sign_citation":"https://pith.science/pith/WMTV52VH6FXNAXGRQQ2NE4DUZJ/action/citation_signature","submit_replication":"https://pith.science/pith/WMTV52VH6FXNAXGRQQ2NE4DUZJ/action/replication_record"}},"created_at":"2026-07-05T09:10:08.388659+00:00","updated_at":"2026-07-05T09:10:08.388659+00:00"}