{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:76PVS2OI6IZ5UTZRCCPCZAWVC5","short_pith_number":"pith:76PVS2OI","schema_version":"1.0","canonical_sha256":"ff9f5969c8f233da4f31109e2c82d5177d165e3906d8c6233151ea45b2852698","source":{"kind":"arxiv","id":"2504.05614","version":1},"attestation_state":"computed","paper":{"title":"Two Intermediate Translations Are Better Than One: Fine-tuning LLMs for Document-level Translation Refinement","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Daimeng Wei, Hao Yang, Junhui Li, Min Zhang, Shimin Tao, Xinglin Lyu, Yichen Dong","submitted_at":"2025-04-08T02:08:07Z","abstract_excerpt":"Recent research has shown that large language models (LLMs) can enhance translation quality through self-refinement. In this paper, we build on this idea by extending the refinement from sentence-level to document-level translation, specifically focusing on document-to-document (Doc2Doc) translation refinement. Since sentence-to-sentence (Sent2Sent) and Doc2Doc translation address different aspects of the translation process, we propose fine-tuning LLMs for translation refinement using two intermediate translations, combining the strengths of both Sent2Sent and Doc2Doc. Additionally, recognizi"},"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":"2504.05614","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-08T02:08:07Z","cross_cats_sorted":[],"title_canon_sha256":"e23c9573130787c1cfcd2644c1d8e5daef734ffbe62961aeb38feecfa238af15","abstract_canon_sha256":"cd5eed2cb3028ade985b42d26d9c43d3ac3d9b0c9110a8a2290e8d07544f98b5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:46:06.754727Z","signature_b64":"XmXk8neOKeShLO/sTiMwK7TeNVYv9kJX5+C9x5/VDdXJenxlCdHr1eiayfZO2egm9I5yomd3xf9EOsmD0EiwAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ff9f5969c8f233da4f31109e2c82d5177d165e3906d8c6233151ea45b2852698","last_reissued_at":"2026-07-05T10:46:06.754155Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:46:06.754155Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Two Intermediate Translations Are Better Than One: Fine-tuning LLMs for Document-level Translation Refinement","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Daimeng Wei, Hao Yang, Junhui Li, Min Zhang, Shimin Tao, Xinglin Lyu, Yichen Dong","submitted_at":"2025-04-08T02:08:07Z","abstract_excerpt":"Recent research has shown that large language models (LLMs) can enhance translation quality through self-refinement. In this paper, we build on this idea by extending the refinement from sentence-level to document-level translation, specifically focusing on document-to-document (Doc2Doc) translation refinement. Since sentence-to-sentence (Sent2Sent) and Doc2Doc translation address different aspects of the translation process, we propose fine-tuning LLMs for translation refinement using two intermediate translations, combining the strengths of both Sent2Sent and Doc2Doc. Additionally, recognizi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.05614","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/2504.05614/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":"2504.05614","created_at":"2026-07-05T10:46:06.754214+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.05614v1","created_at":"2026-07-05T10:46:06.754214+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.05614","created_at":"2026-07-05T10:46:06.754214+00:00"},{"alias_kind":"pith_short_12","alias_value":"76PVS2OI6IZ5","created_at":"2026-07-05T10:46:06.754214+00:00"},{"alias_kind":"pith_short_16","alias_value":"76PVS2OI6IZ5UTZR","created_at":"2026-07-05T10:46:06.754214+00:00"},{"alias_kind":"pith_short_8","alias_value":"76PVS2OI","created_at":"2026-07-05T10:46:06.754214+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"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":191,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/76PVS2OI6IZ5UTZRCCPCZAWVC5","json":"https://pith.science/pith/76PVS2OI6IZ5UTZRCCPCZAWVC5.json","graph_json":"https://pith.science/api/pith-number/76PVS2OI6IZ5UTZRCCPCZAWVC5/graph.json","events_json":"https://pith.science/api/pith-number/76PVS2OI6IZ5UTZRCCPCZAWVC5/events.json","paper":"https://pith.science/paper/76PVS2OI"},"agent_actions":{"view_html":"https://pith.science/pith/76PVS2OI6IZ5UTZRCCPCZAWVC5","download_json":"https://pith.science/pith/76PVS2OI6IZ5UTZRCCPCZAWVC5.json","view_paper":"https://pith.science/paper/76PVS2OI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.05614&json=true","fetch_graph":"https://pith.science/api/pith-number/76PVS2OI6IZ5UTZRCCPCZAWVC5/graph.json","fetch_events":"https://pith.science/api/pith-number/76PVS2OI6IZ5UTZRCCPCZAWVC5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/76PVS2OI6IZ5UTZRCCPCZAWVC5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/76PVS2OI6IZ5UTZRCCPCZAWVC5/action/storage_attestation","attest_author":"https://pith.science/pith/76PVS2OI6IZ5UTZRCCPCZAWVC5/action/author_attestation","sign_citation":"https://pith.science/pith/76PVS2OI6IZ5UTZRCCPCZAWVC5/action/citation_signature","submit_replication":"https://pith.science/pith/76PVS2OI6IZ5UTZRCCPCZAWVC5/action/replication_record"}},"created_at":"2026-07-05T10:46:06.754214+00:00","updated_at":"2026-07-05T10:46:06.754214+00:00"}