{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:VYY57AHZXVYDEJ6MSPVDJ4R2QL","short_pith_number":"pith:VYY57AHZ","schema_version":"1.0","canonical_sha256":"ae31df80f9bd703227cc93ea34f23a82d444cf0a925050a8ef19267e1dda4460","source":{"kind":"arxiv","id":"2501.09431","version":1},"attestation_state":"computed","paper":{"title":"A Survey on Responsible LLMs: Inherent Risk, Malicious Use, and Mitigation Strategy","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CR","cs.CY"],"primary_cat":"cs.AI","authors_text":"Chen Gao, Fengli Xu, Huandong Wang, Jinghua Piao, Tao Jiang, Wenjie Fu, Yingzhou Tang, Yong Li, Yuxi Huang, Zhilong Chen","submitted_at":"2025-01-16T09:59:45Z","abstract_excerpt":"While large language models (LLMs) present significant potential for supporting numerous real-world applications and delivering positive social impacts, they still face significant challenges in terms of the inherent risk of privacy leakage, hallucinated outputs, and value misalignment, and can be maliciously used for generating toxic content and unethical purposes after been jailbroken. Therefore, in this survey, we present a comprehensive review of recent advancements aimed at mitigating these issues, organized across the four phases of LLM development and usage: data collecting and pre-trai"},"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":"2501.09431","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-01-16T09:59:45Z","cross_cats_sorted":["cs.CL","cs.CR","cs.CY"],"title_canon_sha256":"7bff4b21c7a679d545cf91cd8ea1409a55f536e4907dcbb9b7a7a76eed7f95a7","abstract_canon_sha256":"b6f89ed028e2494077e0f9ca8c1bb24b20133f839d1807409147c5ba5b092258"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:01:56.807015Z","signature_b64":"4a0oKDifNTUvXMcUnYxum+TF8ou+48fdTn3vuyluiRsx1F8tMpQQE69PqUTX0aEI9C0JdRjy7iSQP+sYENvxAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ae31df80f9bd703227cc93ea34f23a82d444cf0a925050a8ef19267e1dda4460","last_reissued_at":"2026-07-05T10:01:56.806613Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:01:56.806613Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Survey on Responsible LLMs: Inherent Risk, Malicious Use, and Mitigation Strategy","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CR","cs.CY"],"primary_cat":"cs.AI","authors_text":"Chen Gao, Fengli Xu, Huandong Wang, Jinghua Piao, Tao Jiang, Wenjie Fu, Yingzhou Tang, Yong Li, Yuxi Huang, Zhilong Chen","submitted_at":"2025-01-16T09:59:45Z","abstract_excerpt":"While large language models (LLMs) present significant potential for supporting numerous real-world applications and delivering positive social impacts, they still face significant challenges in terms of the inherent risk of privacy leakage, hallucinated outputs, and value misalignment, and can be maliciously used for generating toxic content and unethical purposes after been jailbroken. Therefore, in this survey, we present a comprehensive review of recent advancements aimed at mitigating these issues, organized across the four phases of LLM development and usage: data collecting and pre-trai"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.09431","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/2501.09431/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":"2501.09431","created_at":"2026-07-05T10:01:56.806669+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.09431v1","created_at":"2026-07-05T10:01:56.806669+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.09431","created_at":"2026-07-05T10:01:56.806669+00:00"},{"alias_kind":"pith_short_12","alias_value":"VYY57AHZXVYD","created_at":"2026-07-05T10:01:56.806669+00:00"},{"alias_kind":"pith_short_16","alias_value":"VYY57AHZXVYDEJ6M","created_at":"2026-07-05T10:01:56.806669+00:00"},{"alias_kind":"pith_short_8","alias_value":"VYY57AHZ","created_at":"2026-07-05T10:01:56.806669+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.22508","citing_title":"AgentStealth: Reinforcing Large Language Model for Anonymizing User-generated Text","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VYY57AHZXVYDEJ6MSPVDJ4R2QL","json":"https://pith.science/pith/VYY57AHZXVYDEJ6MSPVDJ4R2QL.json","graph_json":"https://pith.science/api/pith-number/VYY57AHZXVYDEJ6MSPVDJ4R2QL/graph.json","events_json":"https://pith.science/api/pith-number/VYY57AHZXVYDEJ6MSPVDJ4R2QL/events.json","paper":"https://pith.science/paper/VYY57AHZ"},"agent_actions":{"view_html":"https://pith.science/pith/VYY57AHZXVYDEJ6MSPVDJ4R2QL","download_json":"https://pith.science/pith/VYY57AHZXVYDEJ6MSPVDJ4R2QL.json","view_paper":"https://pith.science/paper/VYY57AHZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.09431&json=true","fetch_graph":"https://pith.science/api/pith-number/VYY57AHZXVYDEJ6MSPVDJ4R2QL/graph.json","fetch_events":"https://pith.science/api/pith-number/VYY57AHZXVYDEJ6MSPVDJ4R2QL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VYY57AHZXVYDEJ6MSPVDJ4R2QL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VYY57AHZXVYDEJ6MSPVDJ4R2QL/action/storage_attestation","attest_author":"https://pith.science/pith/VYY57AHZXVYDEJ6MSPVDJ4R2QL/action/author_attestation","sign_citation":"https://pith.science/pith/VYY57AHZXVYDEJ6MSPVDJ4R2QL/action/citation_signature","submit_replication":"https://pith.science/pith/VYY57AHZXVYDEJ6MSPVDJ4R2QL/action/replication_record"}},"created_at":"2026-07-05T10:01:56.806669+00:00","updated_at":"2026-07-05T10:01:56.806669+00:00"}