{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DMBTOGUGBUQLKV3KX3RFHZTFTP","short_pith_number":"pith:DMBTOGUG","schema_version":"1.0","canonical_sha256":"1b03371a860d20b5576abee253e6659be67f1dfd9fe7bbcb5c8b186cd3ad7127","source":{"kind":"arxiv","id":"2510.04484","version":2},"attestation_state":"computed","paper":{"title":"Psychological Steering in LLMs: An Evaluation of Effectiveness and Trustworthiness","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ala N. Tak, Amin Banayeeanzade, Anahita Bolourani, Emilio Ferrara, Fatemeh Bahrani, Jonathan Gratch, Leonardo Blas, Sai Praneeth Karimireddy","submitted_at":"2025-10-06T04:49:56Z","abstract_excerpt":"The ability to control LLMs' emulated emotional states and personality traits is an essential step in enabling rich, human-centered interactions in socially interactive settings. We introduce PsySET, a Psychologically-informed benchmark to evaluate LLM Steering Effectiveness and Trustworthiness across the emotion and personality domains. Our study spans four models from different LLM families paired with various steering strategies, including prompting, fine-tuning, and representation engineering. Our results indicate that prompting is consistently effective but limited in intensity control, w"},"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":"2510.04484","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-10-06T04:49:56Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a1971f779935d681856fe68b55b0e22a0540156715ad472b854ee230cbe93487","abstract_canon_sha256":"958bdc67c31b44c7c02c93ac80d2ba3c5e074b805c5fe9c568800cc9abaebe20"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-03T01:16:49.519731Z","signature_b64":"UovDqDnwI+1nScv8jX/eeWbg/FpQdw7jFxKih2oEl9+xcChcbgJCMrI3B/pXZtRAMvhrWWnFNFNWMOrWRoJCCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1b03371a860d20b5576abee253e6659be67f1dfd9fe7bbcb5c8b186cd3ad7127","last_reissued_at":"2026-07-03T01:16:49.519197Z","signature_status":"signed_v1","first_computed_at":"2026-07-03T01:16:49.519197Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Psychological Steering in LLMs: An Evaluation of Effectiveness and Trustworthiness","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ala N. Tak, Amin Banayeeanzade, Anahita Bolourani, Emilio Ferrara, Fatemeh Bahrani, Jonathan Gratch, Leonardo Blas, Sai Praneeth Karimireddy","submitted_at":"2025-10-06T04:49:56Z","abstract_excerpt":"The ability to control LLMs' emulated emotional states and personality traits is an essential step in enabling rich, human-centered interactions in socially interactive settings. We introduce PsySET, a Psychologically-informed benchmark to evaluate LLM Steering Effectiveness and Trustworthiness across the emotion and personality domains. Our study spans four models from different LLM families paired with various steering strategies, including prompting, fine-tuning, and representation engineering. Our results indicate that prompting is consistently effective but limited in intensity control, w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.04484","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/2510.04484/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":"2510.04484","created_at":"2026-07-03T01:16:49.519254+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.04484v2","created_at":"2026-07-03T01:16:49.519254+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.04484","created_at":"2026-07-03T01:16:49.519254+00:00"},{"alias_kind":"pith_short_12","alias_value":"DMBTOGUGBUQL","created_at":"2026-07-03T01:16:49.519254+00:00"},{"alias_kind":"pith_short_16","alias_value":"DMBTOGUGBUQLKV3K","created_at":"2026-07-03T01:16:49.519254+00:00"},{"alias_kind":"pith_short_8","alias_value":"DMBTOGUG","created_at":"2026-07-03T01:16:49.519254+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"2601.05437","citing_title":"Tracing Moral Foundations in Large Language Models","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2601.05437","citing_title":"Tracing Moral Foundations in Large Language Models","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2601.14004","citing_title":"Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DMBTOGUGBUQLKV3KX3RFHZTFTP","json":"https://pith.science/pith/DMBTOGUGBUQLKV3KX3RFHZTFTP.json","graph_json":"https://pith.science/api/pith-number/DMBTOGUGBUQLKV3KX3RFHZTFTP/graph.json","events_json":"https://pith.science/api/pith-number/DMBTOGUGBUQLKV3KX3RFHZTFTP/events.json","paper":"https://pith.science/paper/DMBTOGUG"},"agent_actions":{"view_html":"https://pith.science/pith/DMBTOGUGBUQLKV3KX3RFHZTFTP","download_json":"https://pith.science/pith/DMBTOGUGBUQLKV3KX3RFHZTFTP.json","view_paper":"https://pith.science/paper/DMBTOGUG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.04484&json=true","fetch_graph":"https://pith.science/api/pith-number/DMBTOGUGBUQLKV3KX3RFHZTFTP/graph.json","fetch_events":"https://pith.science/api/pith-number/DMBTOGUGBUQLKV3KX3RFHZTFTP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DMBTOGUGBUQLKV3KX3RFHZTFTP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DMBTOGUGBUQLKV3KX3RFHZTFTP/action/storage_attestation","attest_author":"https://pith.science/pith/DMBTOGUGBUQLKV3KX3RFHZTFTP/action/author_attestation","sign_citation":"https://pith.science/pith/DMBTOGUGBUQLKV3KX3RFHZTFTP/action/citation_signature","submit_replication":"https://pith.science/pith/DMBTOGUGBUQLKV3KX3RFHZTFTP/action/replication_record"}},"created_at":"2026-07-03T01:16:49.519254+00:00","updated_at":"2026-07-03T01:16:49.519254+00:00"}