{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:V3PYSLA325QSK4CIFA34H3T4LN","short_pith_number":"pith:V3PYSLA3","schema_version":"1.0","canonical_sha256":"aedf892c1bd7612570482837c3ee7c5b4d40493a7a2dff32ed098dafcc20c803","source":{"kind":"arxiv","id":"2505.24119","version":1},"attestation_state":"computed","paper":{"title":"The State of Multilingual LLM Safety Research: From Measuring the Language Gap to Mitigating It","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Beyza Ermis, Julia Kreutzer, Marzieh Fadaee, Stephen H. Bach, Zheng-Xin Yong","submitted_at":"2025-05-30T01:32:44Z","abstract_excerpt":"This paper presents a comprehensive analysis of the linguistic diversity of LLM safety research, highlighting the English-centric nature of the field. Through a systematic review of nearly 300 publications from 2020--2024 across major NLP conferences and workshops at *ACL, we identify a significant and growing language gap in LLM safety research, with even high-resource non-English languages receiving minimal attention. We further observe that non-English languages are rarely studied as a standalone language and that English safety research exhibits poor language documentation practice. To mot"},"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":"2505.24119","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-30T01:32:44Z","cross_cats_sorted":[],"title_canon_sha256":"ea4f125411107976cb72fad5395936053ce800cf2fdf12dc162f810725f0da86","abstract_canon_sha256":"59d7ac1f977604d0ab102c0e1aeff59c3f0b9a43bb66e363cad6b0b9522e0f4f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:42.306943Z","signature_b64":"gwFskMllGVXSaHx5rVHiH8sgKJT7cfhT6P5r2ggmdMZhmZq/rJT0ciUdnNpgdtWt03duLP/85hjxF69OdE2SCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aedf892c1bd7612570482837c3ee7c5b4d40493a7a2dff32ed098dafcc20c803","last_reissued_at":"2026-07-05T11:12:42.306249Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:42.306249Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The State of Multilingual LLM Safety Research: From Measuring the Language Gap to Mitigating It","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Beyza Ermis, Julia Kreutzer, Marzieh Fadaee, Stephen H. Bach, Zheng-Xin Yong","submitted_at":"2025-05-30T01:32:44Z","abstract_excerpt":"This paper presents a comprehensive analysis of the linguistic diversity of LLM safety research, highlighting the English-centric nature of the field. Through a systematic review of nearly 300 publications from 2020--2024 across major NLP conferences and workshops at *ACL, we identify a significant and growing language gap in LLM safety research, with even high-resource non-English languages receiving minimal attention. We further observe that non-English languages are rarely studied as a standalone language and that English safety research exhibits poor language documentation practice. To mot"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.24119","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/2505.24119/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":"2505.24119","created_at":"2026-07-05T11:12:42.306332+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.24119v1","created_at":"2026-07-05T11:12:42.306332+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.24119","created_at":"2026-07-05T11:12:42.306332+00:00"},{"alias_kind":"pith_short_12","alias_value":"V3PYSLA325QS","created_at":"2026-07-05T11:12:42.306332+00:00"},{"alias_kind":"pith_short_16","alias_value":"V3PYSLA325QSK4CI","created_at":"2026-07-05T11:12:42.306332+00:00"},{"alias_kind":"pith_short_8","alias_value":"V3PYSLA3","created_at":"2026-07-05T11:12:42.306332+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07535","citing_title":"Multilingual Refusal Alignment for Safer Large Language Models","ref_index":70,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25420","citing_title":"SomaliBench Eval: Measuring English-to-Somali Refusal Gaps in Open-Weight Language Models","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2602.11157","citing_title":"Response-Based Knowledge Distillation for Multilingual Jailbreak Prevention Unwittingly Compromises Safety","ref_index":50,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/V3PYSLA325QSK4CIFA34H3T4LN","json":"https://pith.science/pith/V3PYSLA325QSK4CIFA34H3T4LN.json","graph_json":"https://pith.science/api/pith-number/V3PYSLA325QSK4CIFA34H3T4LN/graph.json","events_json":"https://pith.science/api/pith-number/V3PYSLA325QSK4CIFA34H3T4LN/events.json","paper":"https://pith.science/paper/V3PYSLA3"},"agent_actions":{"view_html":"https://pith.science/pith/V3PYSLA325QSK4CIFA34H3T4LN","download_json":"https://pith.science/pith/V3PYSLA325QSK4CIFA34H3T4LN.json","view_paper":"https://pith.science/paper/V3PYSLA3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.24119&json=true","fetch_graph":"https://pith.science/api/pith-number/V3PYSLA325QSK4CIFA34H3T4LN/graph.json","fetch_events":"https://pith.science/api/pith-number/V3PYSLA325QSK4CIFA34H3T4LN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V3PYSLA325QSK4CIFA34H3T4LN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V3PYSLA325QSK4CIFA34H3T4LN/action/storage_attestation","attest_author":"https://pith.science/pith/V3PYSLA325QSK4CIFA34H3T4LN/action/author_attestation","sign_citation":"https://pith.science/pith/V3PYSLA325QSK4CIFA34H3T4LN/action/citation_signature","submit_replication":"https://pith.science/pith/V3PYSLA325QSK4CIFA34H3T4LN/action/replication_record"}},"created_at":"2026-07-05T11:12:42.306332+00:00","updated_at":"2026-07-05T11:12:42.306332+00:00"}