{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:TZCEUNWKEFZYESJLDZJ3AU57G7","short_pith_number":"pith:TZCEUNWK","schema_version":"1.0","canonical_sha256":"9e444a36ca217382492b1e53b053bf37e4b046ce596e2a9414b878080779de71","source":{"kind":"arxiv","id":"2302.07856","version":1},"attestation_state":"computed","paper":{"title":"Dictionary-based Phrase-level Prompting of Large Language Models for Machine Translation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Hila Gonen, Luke Zettlemoyer, Marjan Ghazvininejad","submitted_at":"2023-02-15T18:46:42Z","abstract_excerpt":"Large language models (LLMs) demonstrate remarkable machine translation (MT) abilities via prompting, even though they were not explicitly trained for this task. However, even given the incredible quantities of data they are trained on, LLMs can struggle to translate inputs with rare words, which are common in low resource or domain transfer scenarios. We show that LLM prompting can provide an effective solution for rare words as well, by using prior knowledge from bilingual dictionaries to provide control hints in the prompts. We propose a novel method, DiPMT, that provides a set of possible "},"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":"2302.07856","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-02-15T18:46:42Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ca1d8bd137ca6e028febd4e99dd0cda6a8a53d5d30b7997c55d787b098d392d2","abstract_canon_sha256":"8ff6dc2d12bc5c1af47fa5f65bddc3532cd9b57ee33ae1347dbc8fde3571250c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:42:06.629413Z","signature_b64":"esPyfplyfdhF5dXOpi25wMwwDusfq39tRXv6AcQKPjafn9PSlPDONFAv5hpv5uhWugwPXrIhrVEVqc557NveCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9e444a36ca217382492b1e53b053bf37e4b046ce596e2a9414b878080779de71","last_reissued_at":"2026-07-05T05:42:06.629032Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:42:06.629032Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dictionary-based Phrase-level Prompting of Large Language Models for Machine Translation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Hila Gonen, Luke Zettlemoyer, Marjan Ghazvininejad","submitted_at":"2023-02-15T18:46:42Z","abstract_excerpt":"Large language models (LLMs) demonstrate remarkable machine translation (MT) abilities via prompting, even though they were not explicitly trained for this task. However, even given the incredible quantities of data they are trained on, LLMs can struggle to translate inputs with rare words, which are common in low resource or domain transfer scenarios. We show that LLM prompting can provide an effective solution for rare words as well, by using prior knowledge from bilingual dictionaries to provide control hints in the prompts. We propose a novel method, DiPMT, that provides a set of possible "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.07856","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/2302.07856/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":"2302.07856","created_at":"2026-07-05T05:42:06.629087+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.07856v1","created_at":"2026-07-05T05:42:06.629087+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.07856","created_at":"2026-07-05T05:42:06.629087+00:00"},{"alias_kind":"pith_short_12","alias_value":"TZCEUNWKEFZY","created_at":"2026-07-05T05:42:06.629087+00:00"},{"alias_kind":"pith_short_16","alias_value":"TZCEUNWKEFZYESJL","created_at":"2026-07-05T05:42:06.629087+00:00"},{"alias_kind":"pith_short_8","alias_value":"TZCEUNWK","created_at":"2026-07-05T05:42:06.629087+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.06428","citing_title":"Reinforcement Learning Elicits Contextual Learning of Unseen Language Translation","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06420","citing_title":"A Komi-Yazva--Russian Parallel Corpus and Evaluation Protocol for Zero- and Few-Shot LLM Translation","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23824","citing_title":"Resource-Lean Lexicon Induction for German Dialects","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02035","citing_title":"VIDA: A dataset for Visually Dependent Ambiguity in Multimodal Machine Translation","ref_index":69,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TZCEUNWKEFZYESJLDZJ3AU57G7","json":"https://pith.science/pith/TZCEUNWKEFZYESJLDZJ3AU57G7.json","graph_json":"https://pith.science/api/pith-number/TZCEUNWKEFZYESJLDZJ3AU57G7/graph.json","events_json":"https://pith.science/api/pith-number/TZCEUNWKEFZYESJLDZJ3AU57G7/events.json","paper":"https://pith.science/paper/TZCEUNWK"},"agent_actions":{"view_html":"https://pith.science/pith/TZCEUNWKEFZYESJLDZJ3AU57G7","download_json":"https://pith.science/pith/TZCEUNWKEFZYESJLDZJ3AU57G7.json","view_paper":"https://pith.science/paper/TZCEUNWK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.07856&json=true","fetch_graph":"https://pith.science/api/pith-number/TZCEUNWKEFZYESJLDZJ3AU57G7/graph.json","fetch_events":"https://pith.science/api/pith-number/TZCEUNWKEFZYESJLDZJ3AU57G7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TZCEUNWKEFZYESJLDZJ3AU57G7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TZCEUNWKEFZYESJLDZJ3AU57G7/action/storage_attestation","attest_author":"https://pith.science/pith/TZCEUNWKEFZYESJLDZJ3AU57G7/action/author_attestation","sign_citation":"https://pith.science/pith/TZCEUNWKEFZYESJLDZJ3AU57G7/action/citation_signature","submit_replication":"https://pith.science/pith/TZCEUNWKEFZYESJLDZJ3AU57G7/action/replication_record"}},"created_at":"2026-07-05T05:42:06.629087+00:00","updated_at":"2026-07-05T05:42:06.629087+00:00"}