{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2E3HMBR7I4B3RT6WATNEFD4KA3","short_pith_number":"pith:2E3HMBR7","schema_version":"1.0","canonical_sha256":"d13676063f4703b8cfd604da428f8a06fe647ca5daab8576cc93dee4dec6c4c2","source":{"kind":"arxiv","id":"2401.06568","version":2},"attestation_state":"computed","paper":{"title":"Lost in the Source Language: How Large Language Models Evaluate the Quality of Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jiajun Chen, Shujian Huang, Xiang Geng, Xu Huang, Yichao Du, Zhirui Zhang","submitted_at":"2024-01-12T13:23:21Z","abstract_excerpt":"This study investigates how Large Language Models (LLMs) leverage source and reference data in machine translation evaluation task, aiming to better understand the mechanisms behind their remarkable performance in this task. We design the controlled experiments across various input modes and model types, and employ both coarse-grained and fine-grained prompts to discern the utility of source versus reference information. We find that reference information significantly enhances the evaluation accuracy, while surprisingly, source information sometimes is counterproductive, indicating LLMs' inab"},"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":"2401.06568","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-12T13:23:21Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4324fc6bea84180001e999408f3a5c3acfc6faa745fa371c7fcec72edc3ad48e","abstract_canon_sha256":"ce7ebbb0d8817df5415d221c2d980d21dc2a541d58b943e0ce5f25a9ff873888"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:28:04.831043Z","signature_b64":"yuQViARKm99ic8hIJyavAAb0fdNQEMIvESeLmpAg21mIrS3SmPxSTlSMq+O0GUcqjuZTBeML5dxLto9FNOcTBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d13676063f4703b8cfd604da428f8a06fe647ca5daab8576cc93dee4dec6c4c2","last_reissued_at":"2026-07-05T08:28:04.830597Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:28:04.830597Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Lost in the Source Language: How Large Language Models Evaluate the Quality of Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jiajun Chen, Shujian Huang, Xiang Geng, Xu Huang, Yichao Du, Zhirui Zhang","submitted_at":"2024-01-12T13:23:21Z","abstract_excerpt":"This study investigates how Large Language Models (LLMs) leverage source and reference data in machine translation evaluation task, aiming to better understand the mechanisms behind their remarkable performance in this task. We design the controlled experiments across various input modes and model types, and employ both coarse-grained and fine-grained prompts to discern the utility of source versus reference information. We find that reference information significantly enhances the evaluation accuracy, while surprisingly, source information sometimes is counterproductive, indicating LLMs' inab"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.06568","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/2401.06568/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":"2401.06568","created_at":"2026-07-05T08:28:04.830656+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.06568v2","created_at":"2026-07-05T08:28:04.830656+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.06568","created_at":"2026-07-05T08:28:04.830656+00:00"},{"alias_kind":"pith_short_12","alias_value":"2E3HMBR7I4B3","created_at":"2026-07-05T08:28:04.830656+00:00"},{"alias_kind":"pith_short_16","alias_value":"2E3HMBR7I4B3RT6W","created_at":"2026-07-05T08:28:04.830656+00:00"},{"alias_kind":"pith_short_8","alias_value":"2E3HMBR7","created_at":"2026-07-05T08:28:04.830656+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2E3HMBR7I4B3RT6WATNEFD4KA3","json":"https://pith.science/pith/2E3HMBR7I4B3RT6WATNEFD4KA3.json","graph_json":"https://pith.science/api/pith-number/2E3HMBR7I4B3RT6WATNEFD4KA3/graph.json","events_json":"https://pith.science/api/pith-number/2E3HMBR7I4B3RT6WATNEFD4KA3/events.json","paper":"https://pith.science/paper/2E3HMBR7"},"agent_actions":{"view_html":"https://pith.science/pith/2E3HMBR7I4B3RT6WATNEFD4KA3","download_json":"https://pith.science/pith/2E3HMBR7I4B3RT6WATNEFD4KA3.json","view_paper":"https://pith.science/paper/2E3HMBR7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.06568&json=true","fetch_graph":"https://pith.science/api/pith-number/2E3HMBR7I4B3RT6WATNEFD4KA3/graph.json","fetch_events":"https://pith.science/api/pith-number/2E3HMBR7I4B3RT6WATNEFD4KA3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2E3HMBR7I4B3RT6WATNEFD4KA3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2E3HMBR7I4B3RT6WATNEFD4KA3/action/storage_attestation","attest_author":"https://pith.science/pith/2E3HMBR7I4B3RT6WATNEFD4KA3/action/author_attestation","sign_citation":"https://pith.science/pith/2E3HMBR7I4B3RT6WATNEFD4KA3/action/citation_signature","submit_replication":"https://pith.science/pith/2E3HMBR7I4B3RT6WATNEFD4KA3/action/replication_record"}},"created_at":"2026-07-05T08:28:04.830656+00:00","updated_at":"2026-07-05T08:28:04.830656+00:00"}