{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:3UCT6KDSWEE5ZURZPNMUOUGQOB","short_pith_number":"pith:3UCT6KDS","schema_version":"1.0","canonical_sha256":"dd053f2872b109dcd2397b594750d07057fe50e39bdf258eb9d91ee9244dc009","source":{"kind":"arxiv","id":"2505.19484","version":2},"attestation_state":"computed","paper":{"title":"CulFiT: A Fine-grained Cultural-aware LLM Training Paradigm via Multilingual Critique Data Synthesis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Lisi Chen, Ruixiang Feng, Shen Gao, Shuo Shang, Xiuying Chen","submitted_at":"2025-05-26T04:08:26Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated remarkable capabilities across various tasks, yet they often exhibit a specific cultural biases, neglecting the values and linguistic diversity of low-resource regions. This cultural bias not only undermines universal equality, but also risks reinforcing stereotypes and perpetuating discrimination. To address this, we propose CulFiT, a novel culturally-aware training paradigm that leverages multilingual data and fine-grained reward modeling to enhance cultural sensitivity and inclusivity. Our approach synthesizes diverse cultural-related questions"},"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":"2505.19484","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-26T04:08:26Z","cross_cats_sorted":[],"title_canon_sha256":"6da5c7dfcbcfb0933eec02b33f752f942e95c09edbb74b5eb6a5da7ee0482cd9","abstract_canon_sha256":"a6e03b462bceb741846944ff2dc2a13bb85f1e91203d9fef3f63ba01a57bed21"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:10:10.076061Z","signature_b64":"5xNFrJbAGRltsAwMD1Se1RjEmSMCtsLVFedvj+inZLgMsJ1vdhd6ipWc/JC3/rHGTpyeTLGeda46pTUFHGlfDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dd053f2872b109dcd2397b594750d07057fe50e39bdf258eb9d91ee9244dc009","last_reissued_at":"2026-07-05T11:10:10.075564Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:10:10.075564Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CulFiT: A Fine-grained Cultural-aware LLM Training Paradigm via Multilingual Critique Data Synthesis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Lisi Chen, Ruixiang Feng, Shen Gao, Shuo Shang, Xiuying Chen","submitted_at":"2025-05-26T04:08:26Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated remarkable capabilities across various tasks, yet they often exhibit a specific cultural biases, neglecting the values and linguistic diversity of low-resource regions. This cultural bias not only undermines universal equality, but also risks reinforcing stereotypes and perpetuating discrimination. To address this, we propose CulFiT, a novel culturally-aware training paradigm that leverages multilingual data and fine-grained reward modeling to enhance cultural sensitivity and inclusivity. Our approach synthesizes diverse cultural-related questions"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.19484","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/2505.19484/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":"2505.19484","created_at":"2026-07-05T11:10:10.075628+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.19484v2","created_at":"2026-07-05T11:10:10.075628+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.19484","created_at":"2026-07-05T11:10:10.075628+00:00"},{"alias_kind":"pith_short_12","alias_value":"3UCT6KDSWEE5","created_at":"2026-07-05T11:10:10.075628+00:00"},{"alias_kind":"pith_short_16","alias_value":"3UCT6KDSWEE5ZURZ","created_at":"2026-07-05T11:10:10.075628+00:00"},{"alias_kind":"pith_short_8","alias_value":"3UCT6KDS","created_at":"2026-07-05T11:10:10.075628+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/3UCT6KDSWEE5ZURZPNMUOUGQOB","json":"https://pith.science/pith/3UCT6KDSWEE5ZURZPNMUOUGQOB.json","graph_json":"https://pith.science/api/pith-number/3UCT6KDSWEE5ZURZPNMUOUGQOB/graph.json","events_json":"https://pith.science/api/pith-number/3UCT6KDSWEE5ZURZPNMUOUGQOB/events.json","paper":"https://pith.science/paper/3UCT6KDS"},"agent_actions":{"view_html":"https://pith.science/pith/3UCT6KDSWEE5ZURZPNMUOUGQOB","download_json":"https://pith.science/pith/3UCT6KDSWEE5ZURZPNMUOUGQOB.json","view_paper":"https://pith.science/paper/3UCT6KDS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.19484&json=true","fetch_graph":"https://pith.science/api/pith-number/3UCT6KDSWEE5ZURZPNMUOUGQOB/graph.json","fetch_events":"https://pith.science/api/pith-number/3UCT6KDSWEE5ZURZPNMUOUGQOB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3UCT6KDSWEE5ZURZPNMUOUGQOB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3UCT6KDSWEE5ZURZPNMUOUGQOB/action/storage_attestation","attest_author":"https://pith.science/pith/3UCT6KDSWEE5ZURZPNMUOUGQOB/action/author_attestation","sign_citation":"https://pith.science/pith/3UCT6KDSWEE5ZURZPNMUOUGQOB/action/citation_signature","submit_replication":"https://pith.science/pith/3UCT6KDSWEE5ZURZPNMUOUGQOB/action/replication_record"}},"created_at":"2026-07-05T11:10:10.075628+00:00","updated_at":"2026-07-05T11:10:10.075628+00:00"}