{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YU5WX463YEPNTK7OHN7WEGCU2Z","short_pith_number":"pith:YU5WX463","schema_version":"1.0","canonical_sha256":"c53b6bf3dbc11ed9abee3b7f621854d673bc8b9ad8c89cd8a45f3d4ee0db747d","source":{"kind":"arxiv","id":"2402.08015","version":5},"attestation_state":"computed","paper":{"title":"Walia-LLM: Enhancing Amharic-LLaMA by Integrating Task-Specific and Generative Datasets","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aman Kassahun Wassie, Atnafu Lambebo Tonja, Eyasu Shiferaw Jada, Israel Abebe Azime, Mitiku Yohannes Fuge, Seid Muhie Yimam, Tadesse Destaw Belay, Walelign Tewabe Sewunetie, Yonas Chanie","submitted_at":"2024-02-12T19:25:11Z","abstract_excerpt":"Large language models (LLMs) have received a lot of attention in natural language processing (NLP) research because of their exceptional performance in understanding and generating human languages. However, low-resource languages are left behind due to the unavailability of resources. In this work, we focus on enhancing the LLaMA-2-Amharic model by integrating task-specific and generative datasets to improve language model performance for Amharic. We compile an Amharic instruction fine-tuning dataset and fine-tuned LLaMA-2-Amharic model. The fine-tuned model shows promising results in differen"},"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":"2402.08015","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-12T19:25:11Z","cross_cats_sorted":[],"title_canon_sha256":"be7eabf44691947dc746cd1fb71de86c5b5a9be2159f099ba704d2c88d3689ae","abstract_canon_sha256":"af8c2ef7dbc589bae67341c57b317f7ae18c7b3e0b4bf19ff7a68c0883e3e50a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:13:12.282821Z","signature_b64":"0QN/AkkY4VhpsL2ooc5BznoeZmfEDWCY3dRlWeLId/yp8iCVGWlaePUVAfDym0hUYJte8w2B+i//86Q5VlkpDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c53b6bf3dbc11ed9abee3b7f621854d673bc8b9ad8c89cd8a45f3d4ee0db747d","last_reissued_at":"2026-07-05T08:13:12.282363Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:13:12.282363Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Walia-LLM: Enhancing Amharic-LLaMA by Integrating Task-Specific and Generative Datasets","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aman Kassahun Wassie, Atnafu Lambebo Tonja, Eyasu Shiferaw Jada, Israel Abebe Azime, Mitiku Yohannes Fuge, Seid Muhie Yimam, Tadesse Destaw Belay, Walelign Tewabe Sewunetie, Yonas Chanie","submitted_at":"2024-02-12T19:25:11Z","abstract_excerpt":"Large language models (LLMs) have received a lot of attention in natural language processing (NLP) research because of their exceptional performance in understanding and generating human languages. However, low-resource languages are left behind due to the unavailability of resources. In this work, we focus on enhancing the LLaMA-2-Amharic model by integrating task-specific and generative datasets to improve language model performance for Amharic. We compile an Amharic instruction fine-tuning dataset and fine-tuned LLaMA-2-Amharic model. The fine-tuned model shows promising results in differen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.08015","kind":"arxiv","version":5},"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/2402.08015/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":"2402.08015","created_at":"2026-07-05T08:13:12.282420+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.08015v5","created_at":"2026-07-05T08:13:12.282420+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.08015","created_at":"2026-07-05T08:13:12.282420+00:00"},{"alias_kind":"pith_short_12","alias_value":"YU5WX463YEPN","created_at":"2026-07-05T08:13:12.282420+00:00"},{"alias_kind":"pith_short_16","alias_value":"YU5WX463YEPNTK7O","created_at":"2026-07-05T08:13:12.282420+00:00"},{"alias_kind":"pith_short_8","alias_value":"YU5WX463","created_at":"2026-07-05T08:13:12.282420+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.19356","citing_title":"Optimized Text Embedding Models and Benchmarks for Amharic Passage Retrieval","ref_index":5,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YU5WX463YEPNTK7OHN7WEGCU2Z","json":"https://pith.science/pith/YU5WX463YEPNTK7OHN7WEGCU2Z.json","graph_json":"https://pith.science/api/pith-number/YU5WX463YEPNTK7OHN7WEGCU2Z/graph.json","events_json":"https://pith.science/api/pith-number/YU5WX463YEPNTK7OHN7WEGCU2Z/events.json","paper":"https://pith.science/paper/YU5WX463"},"agent_actions":{"view_html":"https://pith.science/pith/YU5WX463YEPNTK7OHN7WEGCU2Z","download_json":"https://pith.science/pith/YU5WX463YEPNTK7OHN7WEGCU2Z.json","view_paper":"https://pith.science/paper/YU5WX463","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.08015&json=true","fetch_graph":"https://pith.science/api/pith-number/YU5WX463YEPNTK7OHN7WEGCU2Z/graph.json","fetch_events":"https://pith.science/api/pith-number/YU5WX463YEPNTK7OHN7WEGCU2Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YU5WX463YEPNTK7OHN7WEGCU2Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YU5WX463YEPNTK7OHN7WEGCU2Z/action/storage_attestation","attest_author":"https://pith.science/pith/YU5WX463YEPNTK7OHN7WEGCU2Z/action/author_attestation","sign_citation":"https://pith.science/pith/YU5WX463YEPNTK7OHN7WEGCU2Z/action/citation_signature","submit_replication":"https://pith.science/pith/YU5WX463YEPNTK7OHN7WEGCU2Z/action/replication_record"}},"created_at":"2026-07-05T08:13:12.282420+00:00","updated_at":"2026-07-05T08:13:12.282420+00:00"}