{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PPOPZE4J3K5ESBCHETPBUPIZQF","short_pith_number":"pith:PPOPZE4J","schema_version":"1.0","canonical_sha256":"7bdcfc9389daba49044724de1a3d198148da5860c8113fed6ea3e828d4fa34e0","source":{"kind":"arxiv","id":"2406.09948","version":2},"attestation_state":"computed","paper":{"title":"BLEnD: A Benchmark for LLMs on Everyday Knowledge in Diverse Cultures and Languages","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Abinew Ali Ayele, Alice Oh, Anar Sabuhi Rzayev, Carla Perez-Almendros, Dimosthenis Antypas, Eunsu Kim, Hsuvas Borkakoty, Hwaran Lee, Jiho Jin, Jose Camacho-Collados, Junho Myung, Kiwoong Park, Mohammad Taher Pilehvar, Nayeon Lee, Nedjma Ousidhoum, Nina White, Rifki Afina Putri, Seid Muhie Yimam, Shamsuddeen Hassan Muhammad, V\\'ictor Guti\\'errez-Basulto, Yazm\\'in Ib\\'a\\~nez-Garc\\'ia, Yi Zhou","submitted_at":"2024-06-14T11:48:54Z","abstract_excerpt":"Large language models (LLMs) often lack culture-specific knowledge of daily life, especially across diverse regions and non-English languages. Existing benchmarks for evaluating LLMs' cultural sensitivities are limited to a single language or collected from online sources such as Wikipedia, which do not reflect the mundane everyday lifestyles of diverse regions. That is, information about the food people eat for their birthday celebrations, spices they typically use, musical instruments youngsters play, or the sports they practice in school is common cultural knowledge but uncommon in easily c"},"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":"2406.09948","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-14T11:48:54Z","cross_cats_sorted":[],"title_canon_sha256":"4db9dcbc269b85142da21716a7f66f3e11c06e1b98b9069a5298ff9ef75c5ae6","abstract_canon_sha256":"9880f26b63fd9f6b9aad49809dd34ce9d2dc82cac28cf81fceef5a60b5d43318"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:01:34.021542Z","signature_b64":"V6QaDhDLEnaNm8NYCRBSWBD9o5RUrb8X8p7dvYonrtd31wBtb+rwQrIfuZzrRc4y02l9jtAVW39S8PcZt3saDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7bdcfc9389daba49044724de1a3d198148da5860c8113fed6ea3e828d4fa34e0","last_reissued_at":"2026-07-05T10:01:34.021027Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:01:34.021027Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BLEnD: A Benchmark for LLMs on Everyday Knowledge in Diverse Cultures and Languages","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Abinew Ali Ayele, Alice Oh, Anar Sabuhi Rzayev, Carla Perez-Almendros, Dimosthenis Antypas, Eunsu Kim, Hsuvas Borkakoty, Hwaran Lee, Jiho Jin, Jose Camacho-Collados, Junho Myung, Kiwoong Park, Mohammad Taher Pilehvar, Nayeon Lee, Nedjma Ousidhoum, Nina White, Rifki Afina Putri, Seid Muhie Yimam, Shamsuddeen Hassan Muhammad, V\\'ictor Guti\\'errez-Basulto, Yazm\\'in Ib\\'a\\~nez-Garc\\'ia, Yi Zhou","submitted_at":"2024-06-14T11:48:54Z","abstract_excerpt":"Large language models (LLMs) often lack culture-specific knowledge of daily life, especially across diverse regions and non-English languages. Existing benchmarks for evaluating LLMs' cultural sensitivities are limited to a single language or collected from online sources such as Wikipedia, which do not reflect the mundane everyday lifestyles of diverse regions. That is, information about the food people eat for their birthday celebrations, spices they typically use, musical instruments youngsters play, or the sports they practice in school is common cultural knowledge but uncommon in easily c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.09948","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/2406.09948/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":"2406.09948","created_at":"2026-07-05T10:01:34.021091+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.09948v2","created_at":"2026-07-05T10:01:34.021091+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.09948","created_at":"2026-07-05T10:01:34.021091+00:00"},{"alias_kind":"pith_short_12","alias_value":"PPOPZE4J3K5E","created_at":"2026-07-05T10:01:34.021091+00:00"},{"alias_kind":"pith_short_16","alias_value":"PPOPZE4J3K5ESBCH","created_at":"2026-07-05T10:01:34.021091+00:00"},{"alias_kind":"pith_short_8","alias_value":"PPOPZE4J","created_at":"2026-07-05T10:01:34.021091+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23164","citing_title":"Same question, different history: language, national identity, and credit in large language models","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22137","citing_title":"Cross-Lingual Consensus: Aligning Multilingual Cultural Knowledge via Multilingual Self-Consistency","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27636","citing_title":"Simorgh at SemEval-2026 task 7: Region-Aware Hybrid Retrieval for Low-Resource Cultural Reasoning in Multilingual Question Answering","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22828","citing_title":"A Survey of Text and Speech Resources for Hausa and Fongbe: Availability, Quality, and Gaps for NLP Development","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2412.15115","citing_title":"Qwen2.5 Technical Report","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2505.14990","citing_title":"Language Specific Knowledge: Do Models Know Better in X than in English?","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22137","citing_title":"Cross-Lingual Consensus: Aligning Multilingual Cultural Knowledge via Multilingual Self-Consistency","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10843","citing_title":"Training-Free Cultural Alignment of Large Language Models via Persona Disagreement","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19262","citing_title":"CulturALL: Benchmarking Multilingual and Multicultural Competence of LLMs on Grounded Tasks","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PPOPZE4J3K5ESBCHETPBUPIZQF","json":"https://pith.science/pith/PPOPZE4J3K5ESBCHETPBUPIZQF.json","graph_json":"https://pith.science/api/pith-number/PPOPZE4J3K5ESBCHETPBUPIZQF/graph.json","events_json":"https://pith.science/api/pith-number/PPOPZE4J3K5ESBCHETPBUPIZQF/events.json","paper":"https://pith.science/paper/PPOPZE4J"},"agent_actions":{"view_html":"https://pith.science/pith/PPOPZE4J3K5ESBCHETPBUPIZQF","download_json":"https://pith.science/pith/PPOPZE4J3K5ESBCHETPBUPIZQF.json","view_paper":"https://pith.science/paper/PPOPZE4J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.09948&json=true","fetch_graph":"https://pith.science/api/pith-number/PPOPZE4J3K5ESBCHETPBUPIZQF/graph.json","fetch_events":"https://pith.science/api/pith-number/PPOPZE4J3K5ESBCHETPBUPIZQF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PPOPZE4J3K5ESBCHETPBUPIZQF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PPOPZE4J3K5ESBCHETPBUPIZQF/action/storage_attestation","attest_author":"https://pith.science/pith/PPOPZE4J3K5ESBCHETPBUPIZQF/action/author_attestation","sign_citation":"https://pith.science/pith/PPOPZE4J3K5ESBCHETPBUPIZQF/action/citation_signature","submit_replication":"https://pith.science/pith/PPOPZE4J3K5ESBCHETPBUPIZQF/action/replication_record"}},"created_at":"2026-07-05T10:01:34.021091+00:00","updated_at":"2026-07-05T10:01:34.021091+00:00"}