{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HUQJD5WAXUTK7U4BAJAMGVMFFN","short_pith_number":"pith:HUQJD5WA","schema_version":"1.0","canonical_sha256":"3d2091f6c0bd26afd3810240c355852b71fb2aa9c92b1ddd4ab0923300dc74bd","source":{"kind":"arxiv","id":"2401.06468","version":4},"attestation_state":"computed","paper":{"title":"Adapting Large Language Models for Document-Level Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"George Foster, Gholamreza Haffari, Lizhen Qu, Minghao Wu, Thuy-Trang Vu","submitted_at":"2024-01-12T09:29:13Z","abstract_excerpt":"Large language models (LLMs) have significantly advanced various natural language processing (NLP) tasks. Recent research indicates that moderately-sized LLMs often outperform larger ones after task-specific fine-tuning. This study focuses on adapting LLMs for document-level machine translation (DocMT) for specific language pairs. We first investigate the impact of prompt strategies on translation performance and then conduct extensive experiments using two fine-tuning methods, three LLM backbones, and 18 translation tasks across nine language pairs. Our results show that specialized models ca"},"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":"2401.06468","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-12T09:29:13Z","cross_cats_sorted":[],"title_canon_sha256":"bde23e83736dd5cb0c6b8275dc9f3e91c0313da8be05e612774560abafe618f6","abstract_canon_sha256":"a2356547ce65de179c6b67466c2da3d4002089a161687c008f6b17751abbf2ec"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:19:07.196954Z","signature_b64":"RZjoBJTX3tdItEdCWLS1wbpuCcUJWyH3uFOUnEranc7CPE4apl8okaUFSSOr+tOBrSTrJvT9Wz2KD6Q7tbGECA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3d2091f6c0bd26afd3810240c355852b71fb2aa9c92b1ddd4ab0923300dc74bd","last_reissued_at":"2026-07-05T09:19:07.196463Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:19:07.196463Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adapting Large Language Models for Document-Level Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"George Foster, Gholamreza Haffari, Lizhen Qu, Minghao Wu, Thuy-Trang Vu","submitted_at":"2024-01-12T09:29:13Z","abstract_excerpt":"Large language models (LLMs) have significantly advanced various natural language processing (NLP) tasks. Recent research indicates that moderately-sized LLMs often outperform larger ones after task-specific fine-tuning. This study focuses on adapting LLMs for document-level machine translation (DocMT) for specific language pairs. We first investigate the impact of prompt strategies on translation performance and then conduct extensive experiments using two fine-tuning methods, three LLM backbones, and 18 translation tasks across nine language pairs. Our results show that specialized models ca"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.06468","kind":"arxiv","version":4},"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/2401.06468/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":"2401.06468","created_at":"2026-07-05T09:19:07.196530+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.06468v4","created_at":"2026-07-05T09:19:07.196530+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.06468","created_at":"2026-07-05T09:19:07.196530+00:00"},{"alias_kind":"pith_short_12","alias_value":"HUQJD5WAXUTK","created_at":"2026-07-05T09:19:07.196530+00:00"},{"alias_kind":"pith_short_16","alias_value":"HUQJD5WAXUTK7U4B","created_at":"2026-07-05T09:19:07.196530+00:00"},{"alias_kind":"pith_short_8","alias_value":"HUQJD5WA","created_at":"2026-07-05T09:19:07.196530+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07020","citing_title":"MADE: Beyond Scoring via a Multilingual Agentic Diagnosing Engine for Fine-Grained Evaluation Insights","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03078","citing_title":"G^2C-MT: Graph-Guided Context Selection for Document-Level Machine Translation","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29489","citing_title":"Which Tokens Need Context? A Reference-Based Analysis of Translation Responsibility Using Fertility and Entropy","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2504.01919","citing_title":"Bridging the Linguistic Divide: A Survey on Leveraging Large Language Models for Machine Translation","ref_index":182,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13368","citing_title":"What Does LLM Refinement Actually Improve? A Systematic Study on Document-Level Literary Translation","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10176","citing_title":"When Prompts Become Payloads: A Framework for Mitigating SQL Injection Attacks in Large Language Model-Driven Applications","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HUQJD5WAXUTK7U4BAJAMGVMFFN","json":"https://pith.science/pith/HUQJD5WAXUTK7U4BAJAMGVMFFN.json","graph_json":"https://pith.science/api/pith-number/HUQJD5WAXUTK7U4BAJAMGVMFFN/graph.json","events_json":"https://pith.science/api/pith-number/HUQJD5WAXUTK7U4BAJAMGVMFFN/events.json","paper":"https://pith.science/paper/HUQJD5WA"},"agent_actions":{"view_html":"https://pith.science/pith/HUQJD5WAXUTK7U4BAJAMGVMFFN","download_json":"https://pith.science/pith/HUQJD5WAXUTK7U4BAJAMGVMFFN.json","view_paper":"https://pith.science/paper/HUQJD5WA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.06468&json=true","fetch_graph":"https://pith.science/api/pith-number/HUQJD5WAXUTK7U4BAJAMGVMFFN/graph.json","fetch_events":"https://pith.science/api/pith-number/HUQJD5WAXUTK7U4BAJAMGVMFFN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HUQJD5WAXUTK7U4BAJAMGVMFFN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HUQJD5WAXUTK7U4BAJAMGVMFFN/action/storage_attestation","attest_author":"https://pith.science/pith/HUQJD5WAXUTK7U4BAJAMGVMFFN/action/author_attestation","sign_citation":"https://pith.science/pith/HUQJD5WAXUTK7U4BAJAMGVMFFN/action/citation_signature","submit_replication":"https://pith.science/pith/HUQJD5WAXUTK7U4BAJAMGVMFFN/action/replication_record"}},"created_at":"2026-07-05T09:19:07.196530+00:00","updated_at":"2026-07-05T09:19:07.196530+00:00"}