{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:4FINVTNWA2AKPIQYYTGMBJQWUB","short_pith_number":"pith:4FINVTNW","schema_version":"1.0","canonical_sha256":"e150dacdb60680a7a218c4ccc0a616a0412099b19e22f8dc26ffea0ad7e7c631","source":{"kind":"arxiv","id":"2409.11726","version":2},"attestation_state":"computed","paper":{"title":"Revealing and Mitigating the Challenge of Detecting Character Knowledge Errors in LLM Role-Playing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.HC"],"primary_cat":"cs.CL","authors_text":"Jiawei Sheng, Shuaiyi Nie, Tingwen Liu, Wenyuan Zhang, Xinghua Zhang, Yongquan He, Zefeng Zhang","submitted_at":"2024-09-18T06:21:44Z","abstract_excerpt":"Large language model (LLM) role-playing has gained widespread attention. Authentic character knowledge is crucial for constructing realistic LLM role-playing agents. However, existing works usually overlook the exploration of LLMs' ability to detect characters' known knowledge errors (KKE) and unknown knowledge errors (UKE) while playing roles, which would lead to low-quality automatic construction of character trainable corpus. In this paper, we propose RoleKE-Bench to evaluate LLMs' ability to detect errors in KKE and UKE. The results indicate that even the latest LLMs struggle to detect the"},"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":"2409.11726","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-18T06:21:44Z","cross_cats_sorted":["cs.HC"],"title_canon_sha256":"b7f027c588a5289f8e3a5414e7a334af461ae7e5096d405d0f80e2209f4ba113","abstract_canon_sha256":"5643d44490435322a4f96fb8a5a7635fe64ad84e7ccae5a4a62e72c78e7dffce"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:06:08.941976Z","signature_b64":"d1/zktvRHrv9SDCCf6bAGtDZXyS215QDMvJMf5RQhf8xHGYvqwgKtVi90e8rQDecq9CJB6cCW68n5I6JYTJGBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e150dacdb60680a7a218c4ccc0a616a0412099b19e22f8dc26ffea0ad7e7c631","last_reissued_at":"2026-07-05T11:06:08.941401Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:06:08.941401Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Revealing and Mitigating the Challenge of Detecting Character Knowledge Errors in LLM Role-Playing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.HC"],"primary_cat":"cs.CL","authors_text":"Jiawei Sheng, Shuaiyi Nie, Tingwen Liu, Wenyuan Zhang, Xinghua Zhang, Yongquan He, Zefeng Zhang","submitted_at":"2024-09-18T06:21:44Z","abstract_excerpt":"Large language model (LLM) role-playing has gained widespread attention. Authentic character knowledge is crucial for constructing realistic LLM role-playing agents. However, existing works usually overlook the exploration of LLMs' ability to detect characters' known knowledge errors (KKE) and unknown knowledge errors (UKE) while playing roles, which would lead to low-quality automatic construction of character trainable corpus. In this paper, we propose RoleKE-Bench to evaluate LLMs' ability to detect errors in KKE and UKE. The results indicate that even the latest LLMs struggle to detect the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.11726","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/2409.11726/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":"2409.11726","created_at":"2026-07-05T11:06:08.941470+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.11726v2","created_at":"2026-07-05T11:06:08.941470+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.11726","created_at":"2026-07-05T11:06:08.941470+00:00"},{"alias_kind":"pith_short_12","alias_value":"4FINVTNWA2AK","created_at":"2026-07-05T11:06:08.941470+00:00"},{"alias_kind":"pith_short_16","alias_value":"4FINVTNWA2AKPIQY","created_at":"2026-07-05T11:06:08.941470+00:00"},{"alias_kind":"pith_short_8","alias_value":"4FINVTNW","created_at":"2026-07-05T11:06:08.941470+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.14905","citing_title":"Concept Incongruence: An Exploration of Time and Death in Role Playing","ref_index":44,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4FINVTNWA2AKPIQYYTGMBJQWUB","json":"https://pith.science/pith/4FINVTNWA2AKPIQYYTGMBJQWUB.json","graph_json":"https://pith.science/api/pith-number/4FINVTNWA2AKPIQYYTGMBJQWUB/graph.json","events_json":"https://pith.science/api/pith-number/4FINVTNWA2AKPIQYYTGMBJQWUB/events.json","paper":"https://pith.science/paper/4FINVTNW"},"agent_actions":{"view_html":"https://pith.science/pith/4FINVTNWA2AKPIQYYTGMBJQWUB","download_json":"https://pith.science/pith/4FINVTNWA2AKPIQYYTGMBJQWUB.json","view_paper":"https://pith.science/paper/4FINVTNW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.11726&json=true","fetch_graph":"https://pith.science/api/pith-number/4FINVTNWA2AKPIQYYTGMBJQWUB/graph.json","fetch_events":"https://pith.science/api/pith-number/4FINVTNWA2AKPIQYYTGMBJQWUB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4FINVTNWA2AKPIQYYTGMBJQWUB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4FINVTNWA2AKPIQYYTGMBJQWUB/action/storage_attestation","attest_author":"https://pith.science/pith/4FINVTNWA2AKPIQYYTGMBJQWUB/action/author_attestation","sign_citation":"https://pith.science/pith/4FINVTNWA2AKPIQYYTGMBJQWUB/action/citation_signature","submit_replication":"https://pith.science/pith/4FINVTNWA2AKPIQYYTGMBJQWUB/action/replication_record"}},"created_at":"2026-07-05T11:06:08.941470+00:00","updated_at":"2026-07-05T11:06:08.941470+00:00"}