{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:4R7PKKQJMQIHUK5DI5DZY2JCJJ","short_pith_number":"pith:4R7PKKQJ","schema_version":"1.0","canonical_sha256":"e47ef52a0964107a2ba347479c69224a774fea94bd759a4be9529b5d4209b380","source":{"kind":"arxiv","id":"2605.12515","version":1},"attestation_state":"computed","paper":{"title":"Mitigating Cross-Lingual Cultural Inconsistencies in LLMs via Consensus-Driven Preference Optimisation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Consensus-driven preference optimization raises cross-language cultural consistency in multilingual LLMs by up to 0.10 points on a new metric.","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anna Korhonen, Isabelle Augenstein, Lucas Resck","submitted_at":"2026-04-02T14:04:06Z","abstract_excerpt":"Despite their impressive capabilities, multilingual large language models (MLLMs) frequently exhibit inconsistent behaviour when the prompt's language changes. While such adaptation is generally desirable, it becomes a critical failure when a user's identity is explicitly defined. For instance, given a fixed British persona and an ambiguous everyday knowledge query about literature, the prompt's language frequently overwrites the system persona -- yielding Shakespeare in English but Cervantes in Spanish. To robustly quantify this Cross-lingual Cultural Inconsistency, we introduce Singleton Fle"},"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":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2605.12515","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-04-02T14:04:06Z","cross_cats_sorted":[],"title_canon_sha256":"25fcf3c30d3e00395363c679bb258c19c7ff50e91d34601619f56f9f27500b93","abstract_canon_sha256":"925d3356ab40bdd208c2c4436f3bcf640b413cbf4c2603c4068da0dbed78185b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:10:02.917984Z","signature_b64":"opdNJwd92HJBLEW7p2v8WzZsL6kMtBkFvRJm+kAmBQo2+4SYj0nH5BjiavJzTTlEsT50D+j6zTWoOxlO3OmSDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e47ef52a0964107a2ba347479c69224a774fea94bd759a4be9529b5d4209b380","last_reissued_at":"2026-05-18T03:10:02.917458Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:10:02.917458Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mitigating Cross-Lingual Cultural Inconsistencies in LLMs via Consensus-Driven Preference Optimisation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Consensus-driven preference optimization raises cross-language cultural consistency in multilingual LLMs by up to 0.10 points on a new metric.","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anna Korhonen, Isabelle Augenstein, Lucas Resck","submitted_at":"2026-04-02T14:04:06Z","abstract_excerpt":"Despite their impressive capabilities, multilingual large language models (MLLMs) frequently exhibit inconsistent behaviour when the prompt's language changes. While such adaptation is generally desirable, it becomes a critical failure when a user's identity is explicitly defined. For instance, given a fixed British persona and an ambiguous everyday knowledge query about literature, the prompt's language frequently overwrites the system persona -- yielding Shakespeare in English but Cervantes in Spanish. To robustly quantify this Cross-lingual Cultural Inconsistency, we introduce Singleton Fle"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"C-3PO achieves up to a 0.10-point absolute increase in κ_S over unaligned models, outperforming strong prompting and representation steering baselines.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the consensus across languages in C-3PO represents genuine cultural consistency rather than an average that erases valid cultural differences, and that κ_S accurately isolates inconsistency without confounding factors.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Multilingual LLMs display cross-lingual cultural inconsistency that a new metric quantifies and a consensus-driven preference optimization method reduces by up to 0.10 points.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Consensus-driven preference optimization raises cross-language cultural consistency in multilingual LLMs by up to 0.10 points on a new metric.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"59649de43d920e1f6e716a91117de4598af1d6d7fbd0f2e838d7ba34c657a420"},"source":{"id":"2605.12515","kind":"arxiv","version":1},"verdict":{"id":"939a6a76-c957-47cb-bda7-ebc4eebf5cbd","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T21:53:55.907146Z","strongest_claim":"C-3PO achieves up to a 0.10-point absolute increase in κ_S over unaligned models, outperforming strong prompting and representation steering baselines.","one_line_summary":"Multilingual LLMs display cross-lingual cultural inconsistency that a new metric quantifies and a consensus-driven preference optimization method reduces by up to 0.10 points.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the consensus across languages in C-3PO represents genuine cultural consistency rather than an average that erases valid cultural differences, and that κ_S accurately isolates inconsistency without confounding factors.","pith_extraction_headline":"Consensus-driven preference optimization raises cross-language cultural consistency in multilingual LLMs by up to 0.10 points on a new metric."},"references":{"count":32,"sample":[{"doi":"10.18653/v1/2025.emnlp-industry.9","year":2025,"title":"Aligning LLM s for Multilingual Consistency in Enterprise Applications","work_id":"92d41103-eded-4852-a122-f01caabcc787","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.18653/v1/2025.emnlp-main.328","year":2025,"title":"Mengyu Bu, Shaolei Zhang, Zhongjun He, Hua Wu, and Yang Feng. 2025. https://doi.org/10.18653/v1/2025.emnlp-main.328 AlignX : Advancing Multilingual Large Language Models with Multilingual Representati","work_id":"e48cf2ba-6934-4719-bbce-03e61dcc960d","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.1162/coli.a.583","year":2025,"title":"doi: 10.1162/COLI.a.583","work_id":"4619fdd0-b039-4474-aef5-d7fddb980730","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.18653/v1/2025.naacl-long.280","year":2025,"title":"Menglong Cui, Pengzhi Gao, Wei Liu, Jian Luan, and Bin Wang. 2025. https://doi.org/10.18653/v1/2025.naacl-long.280 Multilingual Machine Translation with Open Large Language Models at Practical Scale :","work_id":"1290086c-8eb2-49d2-8698-c7a4448fea7f","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.18653/v1/2022.findings-acl.240","year":2022,"title":"Constanza Fierro and Anders Søgaard. 2022. https://doi.org/10.18653/v1/2022.findings-acl.240 Factual Consistency of Multilingual Pretrained Language Models . In Findings of the Association for Computa","work_id":"032b928a-f659-4fc8-bedc-f7f06739aaa8","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":32,"snapshot_sha256":"edb96773750d68381f7ebe2db1eef5225fef1e44bd62ba2b1ea7bf287d90bcfa","internal_anchors":3},"formal_canon":{"evidence_count":2,"snapshot_sha256":"ff738823566b2123693aaafc0f474fe8c9d524e8c7c483b1ca942f8222117361"},"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":"2605.12515","created_at":"2026-05-18T03:10:02.917535+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.12515v1","created_at":"2026-05-18T03:10:02.917535+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.12515","created_at":"2026-05-18T03:10:02.917535+00:00"},{"alias_kind":"pith_short_12","alias_value":"4R7PKKQJMQIH","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"4R7PKKQJMQIHUK5D","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"4R7PKKQJ","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4R7PKKQJMQIHUK5DI5DZY2JCJJ","json":"https://pith.science/pith/4R7PKKQJMQIHUK5DI5DZY2JCJJ.json","graph_json":"https://pith.science/api/pith-number/4R7PKKQJMQIHUK5DI5DZY2JCJJ/graph.json","events_json":"https://pith.science/api/pith-number/4R7PKKQJMQIHUK5DI5DZY2JCJJ/events.json","paper":"https://pith.science/paper/4R7PKKQJ"},"agent_actions":{"view_html":"https://pith.science/pith/4R7PKKQJMQIHUK5DI5DZY2JCJJ","download_json":"https://pith.science/pith/4R7PKKQJMQIHUK5DI5DZY2JCJJ.json","view_paper":"https://pith.science/paper/4R7PKKQJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.12515&json=true","fetch_graph":"https://pith.science/api/pith-number/4R7PKKQJMQIHUK5DI5DZY2JCJJ/graph.json","fetch_events":"https://pith.science/api/pith-number/4R7PKKQJMQIHUK5DI5DZY2JCJJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4R7PKKQJMQIHUK5DI5DZY2JCJJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4R7PKKQJMQIHUK5DI5DZY2JCJJ/action/storage_attestation","attest_author":"https://pith.science/pith/4R7PKKQJMQIHUK5DI5DZY2JCJJ/action/author_attestation","sign_citation":"https://pith.science/pith/4R7PKKQJMQIHUK5DI5DZY2JCJJ/action/citation_signature","submit_replication":"https://pith.science/pith/4R7PKKQJMQIHUK5DI5DZY2JCJJ/action/replication_record"}},"created_at":"2026-05-18T03:10:02.917535+00:00","updated_at":"2026-05-18T03:10:02.917535+00:00"}