{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FH2ACEDPYSFGMRI2URHLLW3OKK","short_pith_number":"pith:FH2ACEDP","schema_version":"1.0","canonical_sha256":"29f401106fc48a66451aa44eb5db6e52a895ebe54541959a1ef06b917601ca61","source":{"kind":"arxiv","id":"2402.10618","version":2},"attestation_state":"computed","paper":{"title":"Enhancing Role-playing Systems through Aggressive Queries: Evaluation and Improvement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Che Liu, Di Zhang, Fuzheng Zhang, Jiao Ou, Kun Gai, Yihong Tang","submitted_at":"2024-02-16T12:12:05Z","abstract_excerpt":"The advent of Large Language Models (LLMs) has propelled dialogue generation into new realms, particularly in the field of role-playing systems (RPSs). While enhanced with ordinary role-relevant training dialogues, existing LLM-based RPSs still struggle to align with roles when handling intricate and trapped queries in boundary scenarios. In this paper, we design the Modular ORchestrated Trap-setting Interaction SystEm (MORTISE) to benchmark and improve the role-playing LLMs' performance. MORTISE can produce highly role-relevant aggressive queries through the collaborative effort of multiple L"},"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":"2402.10618","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-16T12:12:05Z","cross_cats_sorted":[],"title_canon_sha256":"d4f3fa80507a842a66059a65e04eb863527d19611606dd2dd9e020c844e72258","abstract_canon_sha256":"1baa9468ab24ab23edfef56dbed0ee37cb89a9663be0f12674c35501333f4c37"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:32:11.331534Z","signature_b64":"mOoaaiMqj0Oea1iKAt7RRDrn4bJ5ZNDwATHudSkUgj7lTYD67ZLEYaOYa5e+C9zrW9i1yjCT6VC2KJpxV+c6CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"29f401106fc48a66451aa44eb5db6e52a895ebe54541959a1ef06b917601ca61","last_reissued_at":"2026-07-05T08:32:11.331031Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:32:11.331031Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing Role-playing Systems through Aggressive Queries: Evaluation and Improvement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Che Liu, Di Zhang, Fuzheng Zhang, Jiao Ou, Kun Gai, Yihong Tang","submitted_at":"2024-02-16T12:12:05Z","abstract_excerpt":"The advent of Large Language Models (LLMs) has propelled dialogue generation into new realms, particularly in the field of role-playing systems (RPSs). While enhanced with ordinary role-relevant training dialogues, existing LLM-based RPSs still struggle to align with roles when handling intricate and trapped queries in boundary scenarios. In this paper, we design the Modular ORchestrated Trap-setting Interaction SystEm (MORTISE) to benchmark and improve the role-playing LLMs' performance. MORTISE can produce highly role-relevant aggressive queries through the collaborative effort of multiple L"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.10618","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/2402.10618/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":"2402.10618","created_at":"2026-07-05T08:32:11.331084+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.10618v2","created_at":"2026-07-05T08:32:11.331084+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.10618","created_at":"2026-07-05T08:32:11.331084+00:00"},{"alias_kind":"pith_short_12","alias_value":"FH2ACEDPYSFG","created_at":"2026-07-05T08:32:11.331084+00:00"},{"alias_kind":"pith_short_16","alias_value":"FH2ACEDPYSFGMRI2","created_at":"2026-07-05T08:32:11.331084+00:00"},{"alias_kind":"pith_short_8","alias_value":"FH2ACEDP","created_at":"2026-07-05T08:32:11.331084+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.06366","citing_title":"AI Agent Behavioral Science","ref_index":150,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FH2ACEDPYSFGMRI2URHLLW3OKK","json":"https://pith.science/pith/FH2ACEDPYSFGMRI2URHLLW3OKK.json","graph_json":"https://pith.science/api/pith-number/FH2ACEDPYSFGMRI2URHLLW3OKK/graph.json","events_json":"https://pith.science/api/pith-number/FH2ACEDPYSFGMRI2URHLLW3OKK/events.json","paper":"https://pith.science/paper/FH2ACEDP"},"agent_actions":{"view_html":"https://pith.science/pith/FH2ACEDPYSFGMRI2URHLLW3OKK","download_json":"https://pith.science/pith/FH2ACEDPYSFGMRI2URHLLW3OKK.json","view_paper":"https://pith.science/paper/FH2ACEDP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.10618&json=true","fetch_graph":"https://pith.science/api/pith-number/FH2ACEDPYSFGMRI2URHLLW3OKK/graph.json","fetch_events":"https://pith.science/api/pith-number/FH2ACEDPYSFGMRI2URHLLW3OKK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FH2ACEDPYSFGMRI2URHLLW3OKK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FH2ACEDPYSFGMRI2URHLLW3OKK/action/storage_attestation","attest_author":"https://pith.science/pith/FH2ACEDPYSFGMRI2URHLLW3OKK/action/author_attestation","sign_citation":"https://pith.science/pith/FH2ACEDPYSFGMRI2URHLLW3OKK/action/citation_signature","submit_replication":"https://pith.science/pith/FH2ACEDPYSFGMRI2URHLLW3OKK/action/replication_record"}},"created_at":"2026-07-05T08:32:11.331084+00:00","updated_at":"2026-07-05T08:32:11.331084+00:00"}