{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:23AVWOFDQTE6AQHI6AZTRYBL5Z","short_pith_number":"pith:23AVWOFD","schema_version":"1.0","canonical_sha256":"d6c15b38a384c9e040e8f03338e02bee5fae34903463a068f1d412f769698041","source":{"kind":"arxiv","id":"2301.07069","version":2},"attestation_state":"computed","paper":{"title":"Prompting Large Language Model for Machine Translation: A Case Study","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Alexandra Birch, Barry Haddow, Biao Zhang","submitted_at":"2023-01-17T18:32:06Z","abstract_excerpt":"Research on prompting has shown excellent performance with little or even no supervised training across many tasks. However, prompting for machine translation is still under-explored in the literature. We fill this gap by offering a systematic study on prompting strategies for translation, examining various factors for prompt template and demonstration example selection. We further explore the use of monolingual data and the feasibility of cross-lingual, cross-domain, and sentence-to-document transfer learning in prompting. Extensive experiments with GLM-130B (Zeng et al., 2022) as the testbed"},"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":"2301.07069","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-01-17T18:32:06Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"db39378a56ec5bb136354d5fc0de9bd816fa6dddb9e1b4d58cd34dd0bbc99252","abstract_canon_sha256":"d0d8dd00670382f27417d0a3cd818bfbaf18c754b61ecd1cf2a69163a933d8f5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:34:05.455680Z","signature_b64":"dgS0GY2qN1NtOgDsf2YSG4WRhZCO+y3sJaK7BqWvFzjzbyW818N2cxOf2zY4YE9gHPWx4SpPzRDbWjtv4dnpCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d6c15b38a384c9e040e8f03338e02bee5fae34903463a068f1d412f769698041","last_reissued_at":"2026-07-05T05:34:05.455225Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:34:05.455225Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Prompting Large Language Model for Machine Translation: A Case Study","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Alexandra Birch, Barry Haddow, Biao Zhang","submitted_at":"2023-01-17T18:32:06Z","abstract_excerpt":"Research on prompting has shown excellent performance with little or even no supervised training across many tasks. However, prompting for machine translation is still under-explored in the literature. We fill this gap by offering a systematic study on prompting strategies for translation, examining various factors for prompt template and demonstration example selection. We further explore the use of monolingual data and the feasibility of cross-lingual, cross-domain, and sentence-to-document transfer learning in prompting. Extensive experiments with GLM-130B (Zeng et al., 2022) as the testbed"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.07069","kind":"arxiv","version":2},"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/2301.07069/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":"2301.07069","created_at":"2026-07-05T05:34:05.455288+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.07069v2","created_at":"2026-07-05T05:34:05.455288+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.07069","created_at":"2026-07-05T05:34:05.455288+00:00"},{"alias_kind":"pith_short_12","alias_value":"23AVWOFDQTE6","created_at":"2026-07-05T05:34:05.455288+00:00"},{"alias_kind":"pith_short_16","alias_value":"23AVWOFDQTE6AQHI","created_at":"2026-07-05T05:34:05.455288+00:00"},{"alias_kind":"pith_short_8","alias_value":"23AVWOFD","created_at":"2026-07-05T05:34:05.455288+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.31452","citing_title":"Translation Analytics for Freelancers II: Benchmarking Local LLMs for Confidential Translation Workflows","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2305.13860","citing_title":"Jailbreaking ChatGPT via Prompt Engineering: An Empirical Study","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2305.13860","citing_title":"Jailbreaking ChatGPT via Prompt Engineering: An Empirical Study","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18296","citing_title":"Exploring Concreteness Through a Figurative Lens","ref_index":124,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/23AVWOFDQTE6AQHI6AZTRYBL5Z","json":"https://pith.science/pith/23AVWOFDQTE6AQHI6AZTRYBL5Z.json","graph_json":"https://pith.science/api/pith-number/23AVWOFDQTE6AQHI6AZTRYBL5Z/graph.json","events_json":"https://pith.science/api/pith-number/23AVWOFDQTE6AQHI6AZTRYBL5Z/events.json","paper":"https://pith.science/paper/23AVWOFD"},"agent_actions":{"view_html":"https://pith.science/pith/23AVWOFDQTE6AQHI6AZTRYBL5Z","download_json":"https://pith.science/pith/23AVWOFDQTE6AQHI6AZTRYBL5Z.json","view_paper":"https://pith.science/paper/23AVWOFD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.07069&json=true","fetch_graph":"https://pith.science/api/pith-number/23AVWOFDQTE6AQHI6AZTRYBL5Z/graph.json","fetch_events":"https://pith.science/api/pith-number/23AVWOFDQTE6AQHI6AZTRYBL5Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/23AVWOFDQTE6AQHI6AZTRYBL5Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/23AVWOFDQTE6AQHI6AZTRYBL5Z/action/storage_attestation","attest_author":"https://pith.science/pith/23AVWOFDQTE6AQHI6AZTRYBL5Z/action/author_attestation","sign_citation":"https://pith.science/pith/23AVWOFDQTE6AQHI6AZTRYBL5Z/action/citation_signature","submit_replication":"https://pith.science/pith/23AVWOFDQTE6AQHI6AZTRYBL5Z/action/replication_record"}},"created_at":"2026-07-05T05:34:05.455288+00:00","updated_at":"2026-07-05T05:34:05.455288+00:00"}