{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:27Y2EADLLCZN3YOKHXM5H4N3RU","short_pith_number":"pith:27Y2EADL","schema_version":"1.0","canonical_sha256":"d7f1a2006b58b2dde1ca3dd9d3f1bb8d2f68449918d044e786eecbd1473a1ecd","source":{"kind":"arxiv","id":"2505.13157","version":1},"attestation_state":"computed","paper":{"title":"Role-Playing Evaluation for Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Julian Alvarez, Walter Nuninger, Yassine El Boudouri, Yvan Peter","submitted_at":"2025-05-19T14:18:16Z","abstract_excerpt":"Large Language Models (LLMs) demonstrate a notable capacity for adopting personas and engaging in role-playing. However, evaluating this ability presents significant challenges, as human assessments are resource-intensive and automated evaluations can be biased. To address this, we introduce Role-Playing Eval (RPEval), a novel benchmark designed to assess LLM role-playing capabilities across four key dimensions: emotional understanding, decision-making, moral alignment, and in-character consistency. This article details the construction of RPEval and presents baseline evaluations. Our code and"},"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":"2505.13157","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-19T14:18:16Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0604f175f888c6c94c330dd5f8eb3db32aa3d1267a8b9ad981afae0b18d71d01","abstract_canon_sha256":"095d2d6cddbb1149ad8feb8149dfab0b321c465c4887e69694a65a1ef2b17235"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:05:25.988519Z","signature_b64":"65QTkATdIY4jxetrDaoGWDIzBOnhSAslrV8GOw9DoPbHb4ycDpPH14+j28i4/v3Y2UNuJ3ay5os0d4piUTLrDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d7f1a2006b58b2dde1ca3dd9d3f1bb8d2f68449918d044e786eecbd1473a1ecd","last_reissued_at":"2026-07-05T11:05:25.988035Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:05:25.988035Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Role-Playing Evaluation for Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Julian Alvarez, Walter Nuninger, Yassine El Boudouri, Yvan Peter","submitted_at":"2025-05-19T14:18:16Z","abstract_excerpt":"Large Language Models (LLMs) demonstrate a notable capacity for adopting personas and engaging in role-playing. However, evaluating this ability presents significant challenges, as human assessments are resource-intensive and automated evaluations can be biased. To address this, we introduce Role-Playing Eval (RPEval), a novel benchmark designed to assess LLM role-playing capabilities across four key dimensions: emotional understanding, decision-making, moral alignment, and in-character consistency. This article details the construction of RPEval and presents baseline evaluations. Our code and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.13157","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/2505.13157/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":"2505.13157","created_at":"2026-07-05T11:05:25.988092+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.13157v1","created_at":"2026-07-05T11:05:25.988092+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.13157","created_at":"2026-07-05T11:05:25.988092+00:00"},{"alias_kind":"pith_short_12","alias_value":"27Y2EADLLCZN","created_at":"2026-07-05T11:05:25.988092+00:00"},{"alias_kind":"pith_short_16","alias_value":"27Y2EADLLCZN3YOK","created_at":"2026-07-05T11:05:25.988092+00:00"},{"alias_kind":"pith_short_8","alias_value":"27Y2EADL","created_at":"2026-07-05T11:05:25.988092+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.27025","citing_title":"Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization","ref_index":97,"is_internal_anchor":false},{"citing_arxiv_id":"2511.08565","citing_title":"Moral Susceptibility and Robustness under Persona Role-Play in Large Language Models","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10733","citing_title":"Too Nice to Tell the Truth: Quantifying Agreeableness-Driven Sycophancy in Role-Playing Language Models","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/27Y2EADLLCZN3YOKHXM5H4N3RU","json":"https://pith.science/pith/27Y2EADLLCZN3YOKHXM5H4N3RU.json","graph_json":"https://pith.science/api/pith-number/27Y2EADLLCZN3YOKHXM5H4N3RU/graph.json","events_json":"https://pith.science/api/pith-number/27Y2EADLLCZN3YOKHXM5H4N3RU/events.json","paper":"https://pith.science/paper/27Y2EADL"},"agent_actions":{"view_html":"https://pith.science/pith/27Y2EADLLCZN3YOKHXM5H4N3RU","download_json":"https://pith.science/pith/27Y2EADLLCZN3YOKHXM5H4N3RU.json","view_paper":"https://pith.science/paper/27Y2EADL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.13157&json=true","fetch_graph":"https://pith.science/api/pith-number/27Y2EADLLCZN3YOKHXM5H4N3RU/graph.json","fetch_events":"https://pith.science/api/pith-number/27Y2EADLLCZN3YOKHXM5H4N3RU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/27Y2EADLLCZN3YOKHXM5H4N3RU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/27Y2EADLLCZN3YOKHXM5H4N3RU/action/storage_attestation","attest_author":"https://pith.science/pith/27Y2EADLLCZN3YOKHXM5H4N3RU/action/author_attestation","sign_citation":"https://pith.science/pith/27Y2EADLLCZN3YOKHXM5H4N3RU/action/citation_signature","submit_replication":"https://pith.science/pith/27Y2EADLLCZN3YOKHXM5H4N3RU/action/replication_record"}},"created_at":"2026-07-05T11:05:25.988092+00:00","updated_at":"2026-07-05T11:05:25.988092+00:00"}