{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:46UBTCI6PZ5TS56ITTFUZ7EQTV","short_pith_number":"pith:46UBTCI6","schema_version":"1.0","canonical_sha256":"e7a819891e7e7b3977c89ccb4cfc909d4b3866e8423888c7a6cf9c3b17b43767","source":{"kind":"arxiv","id":"2503.04554","version":1},"attestation_state":"computed","paper":{"title":"Compositional Translation: A Novel LLM-based Approach for Low-resource Machine Translation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Armel Zebaze, Beno\\^it Sagot, Rachel Bawden","submitted_at":"2025-03-06T15:37:31Z","abstract_excerpt":"The ability of generative large language models (LLMs) to perform in-context learning has given rise to a large body of research into how best to prompt models for various natural language processing tasks. Machine Translation (MT) has been shown to benefit from in-context examples, in particular when they are semantically similar to the sentence to translate. In this paper, we propose a new LLM-based translation paradigm, compositional translation, to replace naive few-shot MT with similarity-based demonstrations. An LLM is used to decompose a sentence into simpler phrases, and then to transl"},"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":"2503.04554","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-06T15:37:31Z","cross_cats_sorted":[],"title_canon_sha256":"de91e4e71eb1f2ab99137865b9649f1053e70df28c7ff56132b95924c94936e0","abstract_canon_sha256":"8b1664e29fd536ee9516d0c97f274349d72952e9c768a5f4ffc5b632a171046b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:25:42.148043Z","signature_b64":"nH1RBK4p0NtG0yzcPWtnOThM/ycgvoJ/y89URPpeEEgIlIkz00NVvy64NVJ13/uRAbDA9aqlc6Jz4tfPMHFFCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e7a819891e7e7b3977c89ccb4cfc909d4b3866e8423888c7a6cf9c3b17b43767","last_reissued_at":"2026-07-05T10:25:42.147412Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:25:42.147412Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Compositional Translation: A Novel LLM-based Approach for Low-resource Machine Translation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Armel Zebaze, Beno\\^it Sagot, Rachel Bawden","submitted_at":"2025-03-06T15:37:31Z","abstract_excerpt":"The ability of generative large language models (LLMs) to perform in-context learning has given rise to a large body of research into how best to prompt models for various natural language processing tasks. Machine Translation (MT) has been shown to benefit from in-context examples, in particular when they are semantically similar to the sentence to translate. In this paper, we propose a new LLM-based translation paradigm, compositional translation, to replace naive few-shot MT with similarity-based demonstrations. An LLM is used to decompose a sentence into simpler phrases, and then to transl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.04554","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/2503.04554/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":"2503.04554","created_at":"2026-07-05T10:25:42.147487+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.04554v1","created_at":"2026-07-05T10:25:42.147487+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.04554","created_at":"2026-07-05T10:25:42.147487+00:00"},{"alias_kind":"pith_short_12","alias_value":"46UBTCI6PZ5T","created_at":"2026-07-05T10:25:42.147487+00:00"},{"alias_kind":"pith_short_16","alias_value":"46UBTCI6PZ5TS56I","created_at":"2026-07-05T10:25:42.147487+00:00"},{"alias_kind":"pith_short_8","alias_value":"46UBTCI6","created_at":"2026-07-05T10:25:42.147487+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2504.01919","citing_title":"Bridging the Linguistic Divide: A Survey on Leveraging Large Language Models for Machine Translation","ref_index":89,"is_internal_anchor":false},{"citing_arxiv_id":"2512.17738","citing_title":"When the Gold Standard Isn't Necessarily Standard: Challenges of Evaluating the Translation of User-Generated Content","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/46UBTCI6PZ5TS56ITTFUZ7EQTV","json":"https://pith.science/pith/46UBTCI6PZ5TS56ITTFUZ7EQTV.json","graph_json":"https://pith.science/api/pith-number/46UBTCI6PZ5TS56ITTFUZ7EQTV/graph.json","events_json":"https://pith.science/api/pith-number/46UBTCI6PZ5TS56ITTFUZ7EQTV/events.json","paper":"https://pith.science/paper/46UBTCI6"},"agent_actions":{"view_html":"https://pith.science/pith/46UBTCI6PZ5TS56ITTFUZ7EQTV","download_json":"https://pith.science/pith/46UBTCI6PZ5TS56ITTFUZ7EQTV.json","view_paper":"https://pith.science/paper/46UBTCI6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.04554&json=true","fetch_graph":"https://pith.science/api/pith-number/46UBTCI6PZ5TS56ITTFUZ7EQTV/graph.json","fetch_events":"https://pith.science/api/pith-number/46UBTCI6PZ5TS56ITTFUZ7EQTV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/46UBTCI6PZ5TS56ITTFUZ7EQTV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/46UBTCI6PZ5TS56ITTFUZ7EQTV/action/storage_attestation","attest_author":"https://pith.science/pith/46UBTCI6PZ5TS56ITTFUZ7EQTV/action/author_attestation","sign_citation":"https://pith.science/pith/46UBTCI6PZ5TS56ITTFUZ7EQTV/action/citation_signature","submit_replication":"https://pith.science/pith/46UBTCI6PZ5TS56ITTFUZ7EQTV/action/replication_record"}},"created_at":"2026-07-05T10:25:42.147487+00:00","updated_at":"2026-07-05T10:25:42.147487+00:00"}