{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:R3LN56K3V3D6MHU36R5BQFXADW","short_pith_number":"pith:R3LN56K3","schema_version":"1.0","canonical_sha256":"8ed6def95baec7e61e9bf47a1816e01d8c9ed4db70f3e81dd0d22d29833fa904","source":{"kind":"arxiv","id":"2305.17367","version":1},"attestation_state":"computed","paper":{"title":"Augmenting Large Language Model Translators via Translation Memories","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Abudurexiti Reheman, Bei Li, Chunliang Zhang, Jingbo Zhu, Tong Xiao, Yinqiao Li, Yongyu Mu, Yuchun Fan, Zhiquan Cao","submitted_at":"2023-05-27T04:47:09Z","abstract_excerpt":"Using translation memories (TMs) as prompts is a promising approach to in-context learning of machine translation models. In this work, we take a step towards prompting large language models (LLMs) with TMs and making them better translators. We find that the ability of LLMs to ``understand'' prompts is indeed helpful for making better use of TMs. Experiments show that the results of a pre-trained LLM translator can be greatly improved by using high-quality TM-based prompts. These results are even comparable to those of the state-of-the-art NMT systems which have access to large-scale in-domai"},"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":"2305.17367","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-27T04:47:09Z","cross_cats_sorted":[],"title_canon_sha256":"826eba0471f208ac894c32bbafe7ae17e6bbb8fabba2b385106223d4bafcbf3c","abstract_canon_sha256":"be82566c02331093638067e9011a4465a8e2d9ed1fc3d8262d2a9271a1572642"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:14:27.088646Z","signature_b64":"yAYkzTKTzs46+CEQsQiOEGNEUcduqhJhLeXH+uHynYboSEr0gpG+XzwUKrPbQlU4UXdwGvjDXgabEYqf7h8yAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8ed6def95baec7e61e9bf47a1816e01d8c9ed4db70f3e81dd0d22d29833fa904","last_reissued_at":"2026-07-05T06:14:27.088100Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:14:27.088100Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Augmenting Large Language Model Translators via Translation Memories","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Abudurexiti Reheman, Bei Li, Chunliang Zhang, Jingbo Zhu, Tong Xiao, Yinqiao Li, Yongyu Mu, Yuchun Fan, Zhiquan Cao","submitted_at":"2023-05-27T04:47:09Z","abstract_excerpt":"Using translation memories (TMs) as prompts is a promising approach to in-context learning of machine translation models. In this work, we take a step towards prompting large language models (LLMs) with TMs and making them better translators. We find that the ability of LLMs to ``understand'' prompts is indeed helpful for making better use of TMs. Experiments show that the results of a pre-trained LLM translator can be greatly improved by using high-quality TM-based prompts. These results are even comparable to those of the state-of-the-art NMT systems which have access to large-scale in-domai"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.17367","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/2305.17367/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":"2305.17367","created_at":"2026-07-05T06:14:27.088162+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.17367v1","created_at":"2026-07-05T06:14:27.088162+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.17367","created_at":"2026-07-05T06:14:27.088162+00:00"},{"alias_kind":"pith_short_12","alias_value":"R3LN56K3V3D6","created_at":"2026-07-05T06:14:27.088162+00:00"},{"alias_kind":"pith_short_16","alias_value":"R3LN56K3V3D6MHU3","created_at":"2026-07-05T06:14:27.088162+00:00"},{"alias_kind":"pith_short_8","alias_value":"R3LN56K3","created_at":"2026-07-05T06:14:27.088162+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/R3LN56K3V3D6MHU36R5BQFXADW","json":"https://pith.science/pith/R3LN56K3V3D6MHU36R5BQFXADW.json","graph_json":"https://pith.science/api/pith-number/R3LN56K3V3D6MHU36R5BQFXADW/graph.json","events_json":"https://pith.science/api/pith-number/R3LN56K3V3D6MHU36R5BQFXADW/events.json","paper":"https://pith.science/paper/R3LN56K3"},"agent_actions":{"view_html":"https://pith.science/pith/R3LN56K3V3D6MHU36R5BQFXADW","download_json":"https://pith.science/pith/R3LN56K3V3D6MHU36R5BQFXADW.json","view_paper":"https://pith.science/paper/R3LN56K3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.17367&json=true","fetch_graph":"https://pith.science/api/pith-number/R3LN56K3V3D6MHU36R5BQFXADW/graph.json","fetch_events":"https://pith.science/api/pith-number/R3LN56K3V3D6MHU36R5BQFXADW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R3LN56K3V3D6MHU36R5BQFXADW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R3LN56K3V3D6MHU36R5BQFXADW/action/storage_attestation","attest_author":"https://pith.science/pith/R3LN56K3V3D6MHU36R5BQFXADW/action/author_attestation","sign_citation":"https://pith.science/pith/R3LN56K3V3D6MHU36R5BQFXADW/action/citation_signature","submit_replication":"https://pith.science/pith/R3LN56K3V3D6MHU36R5BQFXADW/action/replication_record"}},"created_at":"2026-07-05T06:14:27.088162+00:00","updated_at":"2026-07-05T06:14:27.088162+00:00"}