{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:GEABRBDRTL7HGKGT6MJPQZ64L5","short_pith_number":"pith:GEABRBDR","schema_version":"1.0","canonical_sha256":"31001884719afe7328d3f312f867dc5f745392625bc7b8369de01a2d944dc5fb","source":{"kind":"arxiv","id":"2307.09705","version":1},"attestation_state":"computed","paper":{"title":"CValues: Measuring the Values of Chinese Large Language Models from Safety to Responsibility","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chao Peng, Fei Huang, Guohai Xu, Haotian Xu, Jiayi Liu, Jinghui Si, Jingren Zhou, Jitao Sang, Ji Zhang, Ming Yan, Peng Yi, Rong Zhang, Xing Gao, Zhuoran Zhou","submitted_at":"2023-07-19T01:22:40Z","abstract_excerpt":"With the rapid evolution of large language models (LLMs), there is a growing concern that they may pose risks or have negative social impacts. Therefore, evaluation of human values alignment is becoming increasingly important. Previous work mainly focuses on assessing the performance of LLMs on certain knowledge and reasoning abilities, while neglecting the alignment to human values, especially in a Chinese context. In this paper, we present CValues, the first Chinese human values evaluation benchmark to measure the alignment ability of LLMs in terms of both safety and responsibility criteria."},"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":"2307.09705","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-07-19T01:22:40Z","cross_cats_sorted":[],"title_canon_sha256":"d9fc77b1d4261addaee1f07e717b184c3798fbc23399a7a53ffbb68f24e7388b","abstract_canon_sha256":"a9810d77fc420c8b0d26a49a705c5b519675c6ef8d775307a05e28eca861d0b8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:32:44.868550Z","signature_b64":"qfKc1E1wVogYVdVrM4PgHjWkMKuOQJJz7znj/peHFV1ycJiqRVz0FIq2yEkqDPC/q1Z7i1FE6kzPFXkTGBWJDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"31001884719afe7328d3f312f867dc5f745392625bc7b8369de01a2d944dc5fb","last_reissued_at":"2026-07-05T06:32:44.868062Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:32:44.868062Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CValues: Measuring the Values of Chinese Large Language Models from Safety to Responsibility","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chao Peng, Fei Huang, Guohai Xu, Haotian Xu, Jiayi Liu, Jinghui Si, Jingren Zhou, Jitao Sang, Ji Zhang, Ming Yan, Peng Yi, Rong Zhang, Xing Gao, Zhuoran Zhou","submitted_at":"2023-07-19T01:22:40Z","abstract_excerpt":"With the rapid evolution of large language models (LLMs), there is a growing concern that they may pose risks or have negative social impacts. Therefore, evaluation of human values alignment is becoming increasingly important. Previous work mainly focuses on assessing the performance of LLMs on certain knowledge and reasoning abilities, while neglecting the alignment to human values, especially in a Chinese context. In this paper, we present CValues, the first Chinese human values evaluation benchmark to measure the alignment ability of LLMs in terms of both safety and responsibility criteria."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.09705","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/2307.09705/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":"2307.09705","created_at":"2026-07-05T06:32:44.868118+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.09705v1","created_at":"2026-07-05T06:32:44.868118+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.09705","created_at":"2026-07-05T06:32:44.868118+00:00"},{"alias_kind":"pith_short_12","alias_value":"GEABRBDRTL7H","created_at":"2026-07-05T06:32:44.868118+00:00"},{"alias_kind":"pith_short_16","alias_value":"GEABRBDRTL7HGKGT","created_at":"2026-07-05T06:32:44.868118+00:00"},{"alias_kind":"pith_short_8","alias_value":"GEABRBDR","created_at":"2026-07-05T06:32:44.868118+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.24414","citing_title":"JT-SAFE-V2: Safety-by-Design Foundation Model with World-Context Data","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28733","citing_title":"Agentic Abstention: Do Agents Know When to Stop Instead of Act?","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22258","citing_title":"Harder to Defend: Towards Chinese Toxicity Attacks via Implicit Enhancement and Obfuscation Rewriting","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2401.05561","citing_title":"TrustLLM: Trustworthiness in Large Language Models","ref_index":232,"is_internal_anchor":false},{"citing_arxiv_id":"2309.10253","citing_title":"GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts","ref_index":69,"is_internal_anchor":false},{"citing_arxiv_id":"2412.05579","citing_title":"LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods","ref_index":264,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GEABRBDRTL7HGKGT6MJPQZ64L5","json":"https://pith.science/pith/GEABRBDRTL7HGKGT6MJPQZ64L5.json","graph_json":"https://pith.science/api/pith-number/GEABRBDRTL7HGKGT6MJPQZ64L5/graph.json","events_json":"https://pith.science/api/pith-number/GEABRBDRTL7HGKGT6MJPQZ64L5/events.json","paper":"https://pith.science/paper/GEABRBDR"},"agent_actions":{"view_html":"https://pith.science/pith/GEABRBDRTL7HGKGT6MJPQZ64L5","download_json":"https://pith.science/pith/GEABRBDRTL7HGKGT6MJPQZ64L5.json","view_paper":"https://pith.science/paper/GEABRBDR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.09705&json=true","fetch_graph":"https://pith.science/api/pith-number/GEABRBDRTL7HGKGT6MJPQZ64L5/graph.json","fetch_events":"https://pith.science/api/pith-number/GEABRBDRTL7HGKGT6MJPQZ64L5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GEABRBDRTL7HGKGT6MJPQZ64L5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GEABRBDRTL7HGKGT6MJPQZ64L5/action/storage_attestation","attest_author":"https://pith.science/pith/GEABRBDRTL7HGKGT6MJPQZ64L5/action/author_attestation","sign_citation":"https://pith.science/pith/GEABRBDRTL7HGKGT6MJPQZ64L5/action/citation_signature","submit_replication":"https://pith.science/pith/GEABRBDRTL7HGKGT6MJPQZ64L5/action/replication_record"}},"created_at":"2026-07-05T06:32:44.868118+00:00","updated_at":"2026-07-05T06:32:44.868118+00:00"}