{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QGTPJITMTU66VFIKKGEEIVDYTR","short_pith_number":"pith:QGTPJITM","schema_version":"1.0","canonical_sha256":"81a6f4a26c9d3dea950a51884454789c74585e39c40ae08cd0c92a1c60bdd075","source":{"kind":"arxiv","id":"2407.18786","version":1},"attestation_state":"computed","paper":{"title":"The power of Prompts: Evaluating and Mitigating Gender Bias in MT with LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aleix Sant, Audrey Mash, Carlos Escolano, Francesca De Luca Fornaciari, Maite Melero","submitted_at":"2024-07-26T14:47:31Z","abstract_excerpt":"This paper studies gender bias in machine translation through the lens of Large Language Models (LLMs). Four widely-used test sets are employed to benchmark various base LLMs, comparing their translation quality and gender bias against state-of-the-art Neural Machine Translation (NMT) models for English to Catalan (En $\\rightarrow$ Ca) and English to Spanish (En $\\rightarrow$ Es) translation directions. Our findings reveal pervasive gender bias across all models, with base LLMs exhibiting a higher degree of bias compared to NMT models. To combat this bias, we explore prompting engineering tech"},"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":"2407.18786","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-26T14:47:31Z","cross_cats_sorted":[],"title_canon_sha256":"563d7da48106777fc3b30a0630be36960e4698a8a3808ea24b3c8641fca52d30","abstract_canon_sha256":"41d5bd244b6aea85cba775b44f950b2414138f72176a801117df129eae4063b2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:48:54.783119Z","signature_b64":"N/XhvHXA75q9T7zpgj+0rYgvmxYlyRAys7CVq0IDmJ3mzXFf9InOTBzJNk4fuJ7j5gareAjLxmN5VRHoJraBAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"81a6f4a26c9d3dea950a51884454789c74585e39c40ae08cd0c92a1c60bdd075","last_reissued_at":"2026-07-05T08:48:54.782702Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:48:54.782702Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The power of Prompts: Evaluating and Mitigating Gender Bias in MT with LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aleix Sant, Audrey Mash, Carlos Escolano, Francesca De Luca Fornaciari, Maite Melero","submitted_at":"2024-07-26T14:47:31Z","abstract_excerpt":"This paper studies gender bias in machine translation through the lens of Large Language Models (LLMs). Four widely-used test sets are employed to benchmark various base LLMs, comparing their translation quality and gender bias against state-of-the-art Neural Machine Translation (NMT) models for English to Catalan (En $\\rightarrow$ Ca) and English to Spanish (En $\\rightarrow$ Es) translation directions. Our findings reveal pervasive gender bias across all models, with base LLMs exhibiting a higher degree of bias compared to NMT models. To combat this bias, we explore prompting engineering tech"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.18786","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/2407.18786/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":"2407.18786","created_at":"2026-07-05T08:48:54.782759+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.18786v1","created_at":"2026-07-05T08:48:54.782759+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.18786","created_at":"2026-07-05T08:48:54.782759+00:00"},{"alias_kind":"pith_short_12","alias_value":"QGTPJITMTU66","created_at":"2026-07-05T08:48:54.782759+00:00"},{"alias_kind":"pith_short_16","alias_value":"QGTPJITMTU66VFIK","created_at":"2026-07-05T08:48:54.782759+00:00"},{"alias_kind":"pith_short_8","alias_value":"QGTPJITM","created_at":"2026-07-05T08:48:54.782759+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.16756","citing_title":"Mitigating Prompt-Induced Cognitive Biases in General-Purpose AI for Software Engineering","ref_index":46,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QGTPJITMTU66VFIKKGEEIVDYTR","json":"https://pith.science/pith/QGTPJITMTU66VFIKKGEEIVDYTR.json","graph_json":"https://pith.science/api/pith-number/QGTPJITMTU66VFIKKGEEIVDYTR/graph.json","events_json":"https://pith.science/api/pith-number/QGTPJITMTU66VFIKKGEEIVDYTR/events.json","paper":"https://pith.science/paper/QGTPJITM"},"agent_actions":{"view_html":"https://pith.science/pith/QGTPJITMTU66VFIKKGEEIVDYTR","download_json":"https://pith.science/pith/QGTPJITMTU66VFIKKGEEIVDYTR.json","view_paper":"https://pith.science/paper/QGTPJITM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.18786&json=true","fetch_graph":"https://pith.science/api/pith-number/QGTPJITMTU66VFIKKGEEIVDYTR/graph.json","fetch_events":"https://pith.science/api/pith-number/QGTPJITMTU66VFIKKGEEIVDYTR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QGTPJITMTU66VFIKKGEEIVDYTR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QGTPJITMTU66VFIKKGEEIVDYTR/action/storage_attestation","attest_author":"https://pith.science/pith/QGTPJITMTU66VFIKKGEEIVDYTR/action/author_attestation","sign_citation":"https://pith.science/pith/QGTPJITMTU66VFIKKGEEIVDYTR/action/citation_signature","submit_replication":"https://pith.science/pith/QGTPJITMTU66VFIKKGEEIVDYTR/action/replication_record"}},"created_at":"2026-07-05T08:48:54.782759+00:00","updated_at":"2026-07-05T08:48:54.782759+00:00"}