{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:37DIG5OO6EXJMUHNQU7L627SJS","short_pith_number":"pith:37DIG5OO","schema_version":"1.0","canonical_sha256":"dfc68375cef12e9650ed853ebf6bf24c8e04e9352cc0835bb53752db74a55430","source":{"kind":"arxiv","id":"2506.04975","version":2},"attestation_state":"computed","paper":{"title":"Evaluating Chinese Large Language Models: The Influence of Persona Assignment on Stereotypes and Safeguards","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CY","authors_text":"Carlo Alberto Bono, Francesco Pierri, Geng Liu, Li Feng, Mengxiao Zhu, Songbo Yang","submitted_at":"2025-06-05T12:47:21Z","abstract_excerpt":"Recent research has highlighted that assigning specific personas to large language models (LLMs) can significantly increase harmful content generation. However, limited attention has been given to persona-driven toxicity in non-Western contexts, particularly in Chinese-based LLMs. In this paper, we perform a large-scale, cross-model analysis of refusal behavior and persona-driven toxicity amplification across four Chinese LLMs, leveraging a comprehensive dataset of over 1,400,000 generated texts. We identify significant disparities in persona-driven refusal behavior, including systematic gende"},"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":"2506.04975","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CY","submitted_at":"2025-06-05T12:47:21Z","cross_cats_sorted":[],"title_canon_sha256":"2f8463037d485a18c4f9a20208ccb80fe11b0cde05bbd100a08d17a23033ad4c","abstract_canon_sha256":"f17c117d1cb72b247110ec536ba33f829b383ddd7fbe779efbc7598df5ea4ebb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-28T01:04:28.569964Z","signature_b64":"GKgGDw0dY/7rglEMxK3CA24Z0E5S5DMCAKDcBe7cWyMrwuMBoY8gYTQn/OGs1jjRPTk8r8gA1Yac/w/DZUSzDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dfc68375cef12e9650ed853ebf6bf24c8e04e9352cc0835bb53752db74a55430","last_reissued_at":"2026-05-28T01:04:28.569262Z","signature_status":"signed_v1","first_computed_at":"2026-05-28T01:04:28.569262Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evaluating Chinese Large Language Models: The Influence of Persona Assignment on Stereotypes and Safeguards","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CY","authors_text":"Carlo Alberto Bono, Francesco Pierri, Geng Liu, Li Feng, Mengxiao Zhu, Songbo Yang","submitted_at":"2025-06-05T12:47:21Z","abstract_excerpt":"Recent research has highlighted that assigning specific personas to large language models (LLMs) can significantly increase harmful content generation. However, limited attention has been given to persona-driven toxicity in non-Western contexts, particularly in Chinese-based LLMs. In this paper, we perform a large-scale, cross-model analysis of refusal behavior and persona-driven toxicity amplification across four Chinese LLMs, leveraging a comprehensive dataset of over 1,400,000 generated texts. We identify significant disparities in persona-driven refusal behavior, including systematic gende"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.04975","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/2506.04975/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":"2506.04975","created_at":"2026-05-28T01:04:28.569352+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.04975v2","created_at":"2026-05-28T01:04:28.569352+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.04975","created_at":"2026-05-28T01:04:28.569352+00:00"},{"alias_kind":"pith_short_12","alias_value":"37DIG5OO6EXJ","created_at":"2026-05-28T01:04:28.569352+00:00"},{"alias_kind":"pith_short_16","alias_value":"37DIG5OO6EXJMUHN","created_at":"2026-05-28T01:04:28.569352+00:00"},{"alias_kind":"pith_short_8","alias_value":"37DIG5OO","created_at":"2026-05-28T01:04:28.569352+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/37DIG5OO6EXJMUHNQU7L627SJS","json":"https://pith.science/pith/37DIG5OO6EXJMUHNQU7L627SJS.json","graph_json":"https://pith.science/api/pith-number/37DIG5OO6EXJMUHNQU7L627SJS/graph.json","events_json":"https://pith.science/api/pith-number/37DIG5OO6EXJMUHNQU7L627SJS/events.json","paper":"https://pith.science/paper/37DIG5OO"},"agent_actions":{"view_html":"https://pith.science/pith/37DIG5OO6EXJMUHNQU7L627SJS","download_json":"https://pith.science/pith/37DIG5OO6EXJMUHNQU7L627SJS.json","view_paper":"https://pith.science/paper/37DIG5OO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.04975&json=true","fetch_graph":"https://pith.science/api/pith-number/37DIG5OO6EXJMUHNQU7L627SJS/graph.json","fetch_events":"https://pith.science/api/pith-number/37DIG5OO6EXJMUHNQU7L627SJS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/37DIG5OO6EXJMUHNQU7L627SJS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/37DIG5OO6EXJMUHNQU7L627SJS/action/storage_attestation","attest_author":"https://pith.science/pith/37DIG5OO6EXJMUHNQU7L627SJS/action/author_attestation","sign_citation":"https://pith.science/pith/37DIG5OO6EXJMUHNQU7L627SJS/action/citation_signature","submit_replication":"https://pith.science/pith/37DIG5OO6EXJMUHNQU7L627SJS/action/replication_record"}},"created_at":"2026-05-28T01:04:28.569352+00:00","updated_at":"2026-05-28T01:04:28.569352+00:00"}