{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:Q3TNZZIORFYQAXZIHNFT6OP7LH","short_pith_number":"pith:Q3TNZZIO","schema_version":"1.0","canonical_sha256":"86e6dce50e8971005f283b4b3f39ff59f0b2b9e89dce52bcc6ce685e19e94528","source":{"kind":"arxiv","id":"2406.15625","version":3},"attestation_state":"computed","paper":{"title":"Shortcomings of LLMs for Low-Resource Translation: Retrieval and Understanding are Both the Problem","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Micha Elsner, Sara Court","submitted_at":"2024-06-21T20:02:22Z","abstract_excerpt":"This work investigates the in-context learning abilities of pretrained large language models (LLMs) when instructed to translate text from a low-resource language into a high-resource language as part of an automated machine translation pipeline. We conduct a set of experiments translating Southern Quechua to Spanish and examine the informativity of various types of context retrieved from a constrained database of digitized pedagogical materials (dictionaries and grammar lessons) and parallel corpora. Using both automatic and human evaluation of model output, we conduct ablation studies that m"},"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":"2406.15625","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-21T20:02:22Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"fe9846ee76873746388c1609ab696271d94e05c855db5115ae41ce00d8d5ca47","abstract_canon_sha256":"929cef8fb5aec7d73e637f83974d589c451b113a5219c80e78fb435848be9652"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:25:44.713135Z","signature_b64":"FcP8GKiVTb6KIGXPt0Rdo2rAFPee6kPL0bXu/fv44d1F/HeLUKdS/a7FdCB6ojN5NxLFufJipj1QpEN9KFwNDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"86e6dce50e8971005f283b4b3f39ff59f0b2b9e89dce52bcc6ce685e19e94528","last_reissued_at":"2026-07-05T09:25:44.712549Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:25:44.712549Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Shortcomings of LLMs for Low-Resource Translation: Retrieval and Understanding are Both the Problem","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Micha Elsner, Sara Court","submitted_at":"2024-06-21T20:02:22Z","abstract_excerpt":"This work investigates the in-context learning abilities of pretrained large language models (LLMs) when instructed to translate text from a low-resource language into a high-resource language as part of an automated machine translation pipeline. We conduct a set of experiments translating Southern Quechua to Spanish and examine the informativity of various types of context retrieved from a constrained database of digitized pedagogical materials (dictionaries and grammar lessons) and parallel corpora. Using both automatic and human evaluation of model output, we conduct ablation studies that m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.15625","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/2406.15625/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":"2406.15625","created_at":"2026-07-05T09:25:44.712617+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.15625v3","created_at":"2026-07-05T09:25:44.712617+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.15625","created_at":"2026-07-05T09:25:44.712617+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q3TNZZIORFYQ","created_at":"2026-07-05T09:25:44.712617+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q3TNZZIORFYQAXZI","created_at":"2026-07-05T09:25:44.712617+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q3TNZZIO","created_at":"2026-07-05T09:25:44.712617+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.17131","citing_title":"LLMsAgainstHate @ NLU of Devanagari Script Languages 2025: Hate Speech Detection and Target Identification in Devanagari Languages via Parameter Efficient Fine-Tuning of LLMs","ref_index":5,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Q3TNZZIORFYQAXZIHNFT6OP7LH","json":"https://pith.science/pith/Q3TNZZIORFYQAXZIHNFT6OP7LH.json","graph_json":"https://pith.science/api/pith-number/Q3TNZZIORFYQAXZIHNFT6OP7LH/graph.json","events_json":"https://pith.science/api/pith-number/Q3TNZZIORFYQAXZIHNFT6OP7LH/events.json","paper":"https://pith.science/paper/Q3TNZZIO"},"agent_actions":{"view_html":"https://pith.science/pith/Q3TNZZIORFYQAXZIHNFT6OP7LH","download_json":"https://pith.science/pith/Q3TNZZIORFYQAXZIHNFT6OP7LH.json","view_paper":"https://pith.science/paper/Q3TNZZIO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.15625&json=true","fetch_graph":"https://pith.science/api/pith-number/Q3TNZZIORFYQAXZIHNFT6OP7LH/graph.json","fetch_events":"https://pith.science/api/pith-number/Q3TNZZIORFYQAXZIHNFT6OP7LH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q3TNZZIORFYQAXZIHNFT6OP7LH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q3TNZZIORFYQAXZIHNFT6OP7LH/action/storage_attestation","attest_author":"https://pith.science/pith/Q3TNZZIORFYQAXZIHNFT6OP7LH/action/author_attestation","sign_citation":"https://pith.science/pith/Q3TNZZIORFYQAXZIHNFT6OP7LH/action/citation_signature","submit_replication":"https://pith.science/pith/Q3TNZZIORFYQAXZIHNFT6OP7LH/action/replication_record"}},"created_at":"2026-07-05T09:25:44.712617+00:00","updated_at":"2026-07-05T09:25:44.712617+00:00"}