{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:EIZQPTNN5ACFTOBB2ZF5UP2FSN","short_pith_number":"pith:EIZQPTNN","schema_version":"1.0","canonical_sha256":"223307cdade80459b821d64bda3f4593601372a9ad1a9ee48b614c4931a1972c","source":{"kind":"arxiv","id":"2410.07054","version":1},"attestation_state":"computed","paper":{"title":"Mitigating the Language Mismatch and Repetition Issues in LLM-based Machine Translation via Model Editing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Chen Ma, Defu Lian, Linqi Song, Weichuan Wang, Ying Wei, Zhaoyi Li","submitted_at":"2024-10-09T16:51:21Z","abstract_excerpt":"Large Language Models (LLMs) have recently revolutionized the NLP field, while they still fall short in some specific down-stream tasks. In the work, we focus on utilizing LLMs to perform machine translation, where we observe that two patterns of errors frequently occur and drastically affect the translation quality: language mismatch and repetition. The work sets out to explore the potential for mitigating these two issues by leveraging model editing methods, e.g., by locating Feed-Forward Network (FFN) neurons or something that are responsible for the errors and deactivating them in the infe"},"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":"2410.07054","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-09T16:51:21Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"20c538fe221ba71ab549247642bd3e45903ab5397537806e1edcf2c06d6c56aa","abstract_canon_sha256":"a3521889684597e3b2efb5c3e034673d223da435c371aa4eb50ee77b0a226d9c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:18:10.347233Z","signature_b64":"COBg0fKcq1UD7hbHGEfN5P16ehcsTldhe9NitijDBB4MMttEAV85YlOHP1YrdUGMVDTc0+OjtsAPrcQVVKpfDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"223307cdade80459b821d64bda3f4593601372a9ad1a9ee48b614c4931a1972c","last_reissued_at":"2026-07-05T09:18:10.346738Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:18:10.346738Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mitigating the Language Mismatch and Repetition Issues in LLM-based Machine Translation via Model Editing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Chen Ma, Defu Lian, Linqi Song, Weichuan Wang, Ying Wei, Zhaoyi Li","submitted_at":"2024-10-09T16:51:21Z","abstract_excerpt":"Large Language Models (LLMs) have recently revolutionized the NLP field, while they still fall short in some specific down-stream tasks. In the work, we focus on utilizing LLMs to perform machine translation, where we observe that two patterns of errors frequently occur and drastically affect the translation quality: language mismatch and repetition. The work sets out to explore the potential for mitigating these two issues by leveraging model editing methods, e.g., by locating Feed-Forward Network (FFN) neurons or something that are responsible for the errors and deactivating them in the infe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.07054","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/2410.07054/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":"2410.07054","created_at":"2026-07-05T09:18:10.346800+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.07054v1","created_at":"2026-07-05T09:18:10.346800+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.07054","created_at":"2026-07-05T09:18:10.346800+00:00"},{"alias_kind":"pith_short_12","alias_value":"EIZQPTNN5ACF","created_at":"2026-07-05T09:18:10.346800+00:00"},{"alias_kind":"pith_short_16","alias_value":"EIZQPTNN5ACFTOBB","created_at":"2026-07-05T09:18:10.346800+00:00"},{"alias_kind":"pith_short_8","alias_value":"EIZQPTNN","created_at":"2026-07-05T09:18:10.346800+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.09156","citing_title":"OmniGen-AR: AutoRegressive Any-to-Image Generation","ref_index":84,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EIZQPTNN5ACFTOBB2ZF5UP2FSN","json":"https://pith.science/pith/EIZQPTNN5ACFTOBB2ZF5UP2FSN.json","graph_json":"https://pith.science/api/pith-number/EIZQPTNN5ACFTOBB2ZF5UP2FSN/graph.json","events_json":"https://pith.science/api/pith-number/EIZQPTNN5ACFTOBB2ZF5UP2FSN/events.json","paper":"https://pith.science/paper/EIZQPTNN"},"agent_actions":{"view_html":"https://pith.science/pith/EIZQPTNN5ACFTOBB2ZF5UP2FSN","download_json":"https://pith.science/pith/EIZQPTNN5ACFTOBB2ZF5UP2FSN.json","view_paper":"https://pith.science/paper/EIZQPTNN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.07054&json=true","fetch_graph":"https://pith.science/api/pith-number/EIZQPTNN5ACFTOBB2ZF5UP2FSN/graph.json","fetch_events":"https://pith.science/api/pith-number/EIZQPTNN5ACFTOBB2ZF5UP2FSN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EIZQPTNN5ACFTOBB2ZF5UP2FSN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EIZQPTNN5ACFTOBB2ZF5UP2FSN/action/storage_attestation","attest_author":"https://pith.science/pith/EIZQPTNN5ACFTOBB2ZF5UP2FSN/action/author_attestation","sign_citation":"https://pith.science/pith/EIZQPTNN5ACFTOBB2ZF5UP2FSN/action/citation_signature","submit_replication":"https://pith.science/pith/EIZQPTNN5ACFTOBB2ZF5UP2FSN/action/replication_record"}},"created_at":"2026-07-05T09:18:10.346800+00:00","updated_at":"2026-07-05T09:18:10.346800+00:00"}