{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZXQJ67536RRTRCXKBCM5K7PDC3","short_pith_number":"pith:ZXQJ6753","schema_version":"1.0","canonical_sha256":"cde09f7fbbf463388aea0899d57de316c3cd28d82e5c404aad0169b971098268","source":{"kind":"arxiv","id":"2402.15061","version":2},"attestation_state":"computed","paper":{"title":"Fine-tuning Large Language Models for Domain-specific Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Feiyan Liu, Hanghai Hong, Jiawei Zheng, Jingsong Su, Shikai Wu, Xiaoli Wang, Yonggui Liang","submitted_at":"2024-02-23T02:24:15Z","abstract_excerpt":"Large language models (LLMs) have shown great potential in domain-specific machine translation (MT). However, one major issue is that LLMs pre-trained on general domain corpus might not generalize well to specific domains due to the lack of domain-specific knowledge. To address this issue, this paper focuses on enhancing the domain-specific MT capability of LLMs, by providing high-quality training datasets and proposing a novel fine-tuning framework denoted by DragFT. DragFT augments LLMs via three techniques: (i) Dictionary-enhanced prompting integrates dictionary information into prompts to "},"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":"2402.15061","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-23T02:24:15Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"9d54141c26ea2d2076f14904329a70e199047497ac9f7a0d441c9328c0b75c74","abstract_canon_sha256":"41403a152d0811e9705c04b731105bf551d9adc247985c86cdf33f45316fc46e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:50:01.236493Z","signature_b64":"ILpXUAh6xZwP7A3IC5BztVjfoh957+5xfeDLrsQ7vChJVyrjyRbGb0uWijaWKK/8oV4QVIvyBzPqchH5Pxh5Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cde09f7fbbf463388aea0899d57de316c3cd28d82e5c404aad0169b971098268","last_reissued_at":"2026-07-05T09:50:01.236062Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:50:01.236062Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fine-tuning Large Language Models for Domain-specific Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Feiyan Liu, Hanghai Hong, Jiawei Zheng, Jingsong Su, Shikai Wu, Xiaoli Wang, Yonggui Liang","submitted_at":"2024-02-23T02:24:15Z","abstract_excerpt":"Large language models (LLMs) have shown great potential in domain-specific machine translation (MT). However, one major issue is that LLMs pre-trained on general domain corpus might not generalize well to specific domains due to the lack of domain-specific knowledge. To address this issue, this paper focuses on enhancing the domain-specific MT capability of LLMs, by providing high-quality training datasets and proposing a novel fine-tuning framework denoted by DragFT. DragFT augments LLMs via three techniques: (i) Dictionary-enhanced prompting integrates dictionary information into prompts to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.15061","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/2402.15061/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":"2402.15061","created_at":"2026-07-05T09:50:01.236119+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.15061v2","created_at":"2026-07-05T09:50:01.236119+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.15061","created_at":"2026-07-05T09:50:01.236119+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZXQJ67536RRT","created_at":"2026-07-05T09:50:01.236119+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZXQJ67536RRTRCXK","created_at":"2026-07-05T09:50:01.236119+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZXQJ6753","created_at":"2026-07-05T09:50:01.236119+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"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":131,"is_internal_anchor":false},{"citing_arxiv_id":"2505.00017","citing_title":"ReCellTy: Domain-Specific Knowledge Graph Retrieval-Augmented LLMs Reasoning Workflow for Single-Cell Annotation","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2510.01379","citing_title":"Multi-LLM Orchestration for High-Quality Code Generation: Exploiting Complementary Model Strengths","ref_index":72,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27143","citing_title":"Enhancing Linux Privilege Escalation Attack Capabilities of Local LLM Agents","ref_index":37,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZXQJ67536RRTRCXKBCM5K7PDC3","json":"https://pith.science/pith/ZXQJ67536RRTRCXKBCM5K7PDC3.json","graph_json":"https://pith.science/api/pith-number/ZXQJ67536RRTRCXKBCM5K7PDC3/graph.json","events_json":"https://pith.science/api/pith-number/ZXQJ67536RRTRCXKBCM5K7PDC3/events.json","paper":"https://pith.science/paper/ZXQJ6753"},"agent_actions":{"view_html":"https://pith.science/pith/ZXQJ67536RRTRCXKBCM5K7PDC3","download_json":"https://pith.science/pith/ZXQJ67536RRTRCXKBCM5K7PDC3.json","view_paper":"https://pith.science/paper/ZXQJ6753","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.15061&json=true","fetch_graph":"https://pith.science/api/pith-number/ZXQJ67536RRTRCXKBCM5K7PDC3/graph.json","fetch_events":"https://pith.science/api/pith-number/ZXQJ67536RRTRCXKBCM5K7PDC3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZXQJ67536RRTRCXKBCM5K7PDC3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZXQJ67536RRTRCXKBCM5K7PDC3/action/storage_attestation","attest_author":"https://pith.science/pith/ZXQJ67536RRTRCXKBCM5K7PDC3/action/author_attestation","sign_citation":"https://pith.science/pith/ZXQJ67536RRTRCXKBCM5K7PDC3/action/citation_signature","submit_replication":"https://pith.science/pith/ZXQJ67536RRTRCXKBCM5K7PDC3/action/replication_record"}},"created_at":"2026-07-05T09:50:01.236119+00:00","updated_at":"2026-07-05T09:50:01.236119+00:00"}