{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:T5ZR7CZT76JGJOUSY2WO63GU52","short_pith_number":"pith:T5ZR7CZT","schema_version":"1.0","canonical_sha256":"9f731f8b33ff9264ba92c6acef6cd4eea7ae946abe660ed5acfb8a23cbeb8819","source":{"kind":"arxiv","id":"2402.10811","version":2},"attestation_state":"computed","paper":{"title":"Quantifying the Persona Effect in LLM Simulations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CY"],"primary_cat":"cs.CL","authors_text":"Nigel Collier, Tiancheng Hu","submitted_at":"2024-02-16T16:35:35Z","abstract_excerpt":"Large language models (LLMs) have shown remarkable promise in simulating human language and behavior. This study investigates how integrating persona variables-demographic, social, and behavioral factors-impacts LLMs' ability to simulate diverse perspectives. We find that persona variables account for <10% variance in annotations in existing subjective NLP datasets. Nonetheless, incorporating persona variables via prompting in LLMs provides modest but statistically significant improvements. Persona prompting is most effective in samples where many annotators disagree, but their disagreements a"},"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":"2402.10811","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-16T16:35:35Z","cross_cats_sorted":["cs.CY"],"title_canon_sha256":"26b147fb2df07b47f3e3b8c6c0d212332d6ae22d575b3d7e181159b3b439a3a5","abstract_canon_sha256":"cf9ec72fe33dcb8871711a40612966187362f68692fc73d1be7e02c0b5f26be1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:32:36.840041Z","signature_b64":"TMBoXrAgQWHG/K8k/XByPD+ssK0ZMwioFsPX/qElYOh0BprGXjD3NGvkkel6CP59FQC8Q8a7rzSe/5U1c6guBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9f731f8b33ff9264ba92c6acef6cd4eea7ae946abe660ed5acfb8a23cbeb8819","last_reissued_at":"2026-07-05T08:32:36.839561Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:32:36.839561Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Quantifying the Persona Effect in LLM Simulations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CY"],"primary_cat":"cs.CL","authors_text":"Nigel Collier, Tiancheng Hu","submitted_at":"2024-02-16T16:35:35Z","abstract_excerpt":"Large language models (LLMs) have shown remarkable promise in simulating human language and behavior. This study investigates how integrating persona variables-demographic, social, and behavioral factors-impacts LLMs' ability to simulate diverse perspectives. We find that persona variables account for <10% variance in annotations in existing subjective NLP datasets. Nonetheless, incorporating persona variables via prompting in LLMs provides modest but statistically significant improvements. Persona prompting is most effective in samples where many annotators disagree, but their disagreements a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.10811","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/2402.10811/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":"2402.10811","created_at":"2026-07-05T08:32:36.839619+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.10811v2","created_at":"2026-07-05T08:32:36.839619+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.10811","created_at":"2026-07-05T08:32:36.839619+00:00"},{"alias_kind":"pith_short_12","alias_value":"T5ZR7CZT76JG","created_at":"2026-07-05T08:32:36.839619+00:00"},{"alias_kind":"pith_short_16","alias_value":"T5ZR7CZT76JGJOUS","created_at":"2026-07-05T08:32:36.839619+00:00"},{"alias_kind":"pith_short_8","alias_value":"T5ZR7CZT","created_at":"2026-07-05T08:32:36.839619+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.28187","citing_title":"Whose Name Comes Up? III: Persona Prompting Effects in LLM-Based Scholar Recommendation","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2509.10746","citing_title":"RECAP: Transparent Inference-Time Emotion Alignment for Medical Dialogue Systems","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2510.22170","citing_title":"Measure what Matters: Psychometric Evaluation of AI with Situational Judgment Tests","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13497","citing_title":"Task-Aware Automated User Profile Generation for Recommendation Simulation Using Large Language Models","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08525","citing_title":"Ads in AI Chatbots? An Analysis of How Large Language Models Navigate Conflicts of Interest","ref_index":47,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/T5ZR7CZT76JGJOUSY2WO63GU52","json":"https://pith.science/pith/T5ZR7CZT76JGJOUSY2WO63GU52.json","graph_json":"https://pith.science/api/pith-number/T5ZR7CZT76JGJOUSY2WO63GU52/graph.json","events_json":"https://pith.science/api/pith-number/T5ZR7CZT76JGJOUSY2WO63GU52/events.json","paper":"https://pith.science/paper/T5ZR7CZT"},"agent_actions":{"view_html":"https://pith.science/pith/T5ZR7CZT76JGJOUSY2WO63GU52","download_json":"https://pith.science/pith/T5ZR7CZT76JGJOUSY2WO63GU52.json","view_paper":"https://pith.science/paper/T5ZR7CZT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.10811&json=true","fetch_graph":"https://pith.science/api/pith-number/T5ZR7CZT76JGJOUSY2WO63GU52/graph.json","fetch_events":"https://pith.science/api/pith-number/T5ZR7CZT76JGJOUSY2WO63GU52/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T5ZR7CZT76JGJOUSY2WO63GU52/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T5ZR7CZT76JGJOUSY2WO63GU52/action/storage_attestation","attest_author":"https://pith.science/pith/T5ZR7CZT76JGJOUSY2WO63GU52/action/author_attestation","sign_citation":"https://pith.science/pith/T5ZR7CZT76JGJOUSY2WO63GU52/action/citation_signature","submit_replication":"https://pith.science/pith/T5ZR7CZT76JGJOUSY2WO63GU52/action/replication_record"}},"created_at":"2026-07-05T08:32:36.839619+00:00","updated_at":"2026-07-05T08:32:36.839619+00:00"}