{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PIY4XFMOKXWXWED23PELGUAWW5","short_pith_number":"pith:PIY4XFMO","schema_version":"1.0","canonical_sha256":"7a31cb958e55ed7b107adbc8b35016b7632f842646640fc3922a25cb0ff8cd9a","source":{"kind":"arxiv","id":"2406.07081","version":1},"attestation_state":"computed","paper":{"title":"Efficiently Exploring Large Language Models for Document-Level Machine Translation with In-context Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Deyi Xiong, Jiangcun Du, Menglong Cui, Shaolin Zhu","submitted_at":"2024-06-11T09:11:17Z","abstract_excerpt":"Large language models (LLMs) exhibit outstanding performance in machine translation via in-context learning. In contrast to sentence-level translation, document-level translation (DOCMT) by LLMs based on in-context learning faces two major challenges: firstly, document translations generated by LLMs are often incoherent; secondly, the length of demonstration for in-context learning is usually limited. To address these issues, we propose a Context-Aware Prompting method (CAP), which enables LLMs to generate more accurate, cohesive, and coherent translations via in-context learning. CAP takes in"},"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":"2406.07081","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-11T09:11:17Z","cross_cats_sorted":[],"title_canon_sha256":"b5f145a6a530d0dc75cff1991debf88c549c96f7051318d6d64ee3875043d4d9","abstract_canon_sha256":"a9f2fcd11d4d81294ee88cd946c116bdefbcc0b3bba6ca64602a53c2e1ed22f4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:30:18.134973Z","signature_b64":"wI/eWay9W3QckTGhUHUBSaA6TgCaK2UvacIkEdEHRTRTMStdWbZa8XRwoV84Qig8JALo+Is2dwKbyyAzNqlPAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7a31cb958e55ed7b107adbc8b35016b7632f842646640fc3922a25cb0ff8cd9a","last_reissued_at":"2026-07-05T08:30:18.134491Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:30:18.134491Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficiently Exploring Large Language Models for Document-Level Machine Translation with In-context Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Deyi Xiong, Jiangcun Du, Menglong Cui, Shaolin Zhu","submitted_at":"2024-06-11T09:11:17Z","abstract_excerpt":"Large language models (LLMs) exhibit outstanding performance in machine translation via in-context learning. In contrast to sentence-level translation, document-level translation (DOCMT) by LLMs based on in-context learning faces two major challenges: firstly, document translations generated by LLMs are often incoherent; secondly, the length of demonstration for in-context learning is usually limited. To address these issues, we propose a Context-Aware Prompting method (CAP), which enables LLMs to generate more accurate, cohesive, and coherent translations via in-context learning. CAP takes in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.07081","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/2406.07081/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":"2406.07081","created_at":"2026-07-05T08:30:18.134548+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.07081v1","created_at":"2026-07-05T08:30:18.134548+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.07081","created_at":"2026-07-05T08:30:18.134548+00:00"},{"alias_kind":"pith_short_12","alias_value":"PIY4XFMOKXWX","created_at":"2026-07-05T08:30:18.134548+00:00"},{"alias_kind":"pith_short_16","alias_value":"PIY4XFMOKXWXWED2","created_at":"2026-07-05T08:30:18.134548+00:00"},{"alias_kind":"pith_short_8","alias_value":"PIY4XFMO","created_at":"2026-07-05T08:30:18.134548+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.03078","citing_title":"G^2C-MT: Graph-Guided Context Selection for Document-Level Machine Translation","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PIY4XFMOKXWXWED23PELGUAWW5","json":"https://pith.science/pith/PIY4XFMOKXWXWED23PELGUAWW5.json","graph_json":"https://pith.science/api/pith-number/PIY4XFMOKXWXWED23PELGUAWW5/graph.json","events_json":"https://pith.science/api/pith-number/PIY4XFMOKXWXWED23PELGUAWW5/events.json","paper":"https://pith.science/paper/PIY4XFMO"},"agent_actions":{"view_html":"https://pith.science/pith/PIY4XFMOKXWXWED23PELGUAWW5","download_json":"https://pith.science/pith/PIY4XFMOKXWXWED23PELGUAWW5.json","view_paper":"https://pith.science/paper/PIY4XFMO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.07081&json=true","fetch_graph":"https://pith.science/api/pith-number/PIY4XFMOKXWXWED23PELGUAWW5/graph.json","fetch_events":"https://pith.science/api/pith-number/PIY4XFMOKXWXWED23PELGUAWW5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PIY4XFMOKXWXWED23PELGUAWW5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PIY4XFMOKXWXWED23PELGUAWW5/action/storage_attestation","attest_author":"https://pith.science/pith/PIY4XFMOKXWXWED23PELGUAWW5/action/author_attestation","sign_citation":"https://pith.science/pith/PIY4XFMOKXWXWED23PELGUAWW5/action/citation_signature","submit_replication":"https://pith.science/pith/PIY4XFMOKXWXWED23PELGUAWW5/action/replication_record"}},"created_at":"2026-07-05T08:30:18.134548+00:00","updated_at":"2026-07-05T08:30:18.134548+00:00"}