{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YYTSWQG2J4ZQML2X356PSV4V55","short_pith_number":"pith:YYTSWQG2","schema_version":"1.0","canonical_sha256":"c6272b40da4f33062f57df7cf95795ef547d79d3a0497cc76f62ae8113949ff0","source":{"kind":"arxiv","id":"2410.16491","version":3},"attestation_state":"computed","paper":{"title":"BIG5-CHAT: Shaping LLM Personalities Through Training on Human-Grounded Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Andy Liu, Jiarui Liu, Maarten Sap, Mona Diab, Wenkai Li, Xuhui Zhou","submitted_at":"2024-10-21T20:32:27Z","abstract_excerpt":"In this work, we tackle the challenge of embedding realistic human personality traits into LLMs. Previous approaches have primarily focused on prompt-based methods that describe the behavior associated with the desired personality traits, suffering from realism and validity issues. To address these limitations, we introduce BIG5-CHAT, a large-scale dataset containing 100,000 dialogues designed to ground models in how humans express their personality in language. Leveraging this dataset, we explore Supervised Fine-Tuning and Direct Preference Optimization as training-based methods to align LLMs"},"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":"2410.16491","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-21T20:32:27Z","cross_cats_sorted":[],"title_canon_sha256":"54cb9c374714afff2571be4496d6f782742044fe6d087bcb23e493feacc552b9","abstract_canon_sha256":"1f46d75e308d4a0e390aeb5a11e540cf9faffc3df34d48f5e0afbb4ed2933cc9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:44:42.361672Z","signature_b64":"Kgy5fCf8AaDhHypaYXo3Jh59/lIOzCr8FV3SyoRLG0e12fC0xIzhYW72pFltJKILi+vwzWILRwI57H2PtzbOAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c6272b40da4f33062f57df7cf95795ef547d79d3a0497cc76f62ae8113949ff0","last_reissued_at":"2026-07-05T11:44:42.361091Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:44:42.361091Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BIG5-CHAT: Shaping LLM Personalities Through Training on Human-Grounded Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Andy Liu, Jiarui Liu, Maarten Sap, Mona Diab, Wenkai Li, Xuhui Zhou","submitted_at":"2024-10-21T20:32:27Z","abstract_excerpt":"In this work, we tackle the challenge of embedding realistic human personality traits into LLMs. Previous approaches have primarily focused on prompt-based methods that describe the behavior associated with the desired personality traits, suffering from realism and validity issues. To address these limitations, we introduce BIG5-CHAT, a large-scale dataset containing 100,000 dialogues designed to ground models in how humans express their personality in language. Leveraging this dataset, we explore Supervised Fine-Tuning and Direct Preference Optimization as training-based methods to align LLMs"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.16491","kind":"arxiv","version":3},"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/2410.16491/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":"2410.16491","created_at":"2026-07-05T11:44:42.361158+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.16491v3","created_at":"2026-07-05T11:44:42.361158+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.16491","created_at":"2026-07-05T11:44:42.361158+00:00"},{"alias_kind":"pith_short_12","alias_value":"YYTSWQG2J4ZQ","created_at":"2026-07-05T11:44:42.361158+00:00"},{"alias_kind":"pith_short_16","alias_value":"YYTSWQG2J4ZQML2X","created_at":"2026-07-05T11:44:42.361158+00:00"},{"alias_kind":"pith_short_8","alias_value":"YYTSWQG2","created_at":"2026-07-05T11:44:42.361158+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11074","citing_title":"Modeling Complex Behaviors: Multi-Personality Composition and Dynamic Switching in Vision-Language Models","ref_index":79,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YYTSWQG2J4ZQML2X356PSV4V55","json":"https://pith.science/pith/YYTSWQG2J4ZQML2X356PSV4V55.json","graph_json":"https://pith.science/api/pith-number/YYTSWQG2J4ZQML2X356PSV4V55/graph.json","events_json":"https://pith.science/api/pith-number/YYTSWQG2J4ZQML2X356PSV4V55/events.json","paper":"https://pith.science/paper/YYTSWQG2"},"agent_actions":{"view_html":"https://pith.science/pith/YYTSWQG2J4ZQML2X356PSV4V55","download_json":"https://pith.science/pith/YYTSWQG2J4ZQML2X356PSV4V55.json","view_paper":"https://pith.science/paper/YYTSWQG2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.16491&json=true","fetch_graph":"https://pith.science/api/pith-number/YYTSWQG2J4ZQML2X356PSV4V55/graph.json","fetch_events":"https://pith.science/api/pith-number/YYTSWQG2J4ZQML2X356PSV4V55/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YYTSWQG2J4ZQML2X356PSV4V55/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YYTSWQG2J4ZQML2X356PSV4V55/action/storage_attestation","attest_author":"https://pith.science/pith/YYTSWQG2J4ZQML2X356PSV4V55/action/author_attestation","sign_citation":"https://pith.science/pith/YYTSWQG2J4ZQML2X356PSV4V55/action/citation_signature","submit_replication":"https://pith.science/pith/YYTSWQG2J4ZQML2X356PSV4V55/action/replication_record"}},"created_at":"2026-07-05T11:44:42.361158+00:00","updated_at":"2026-07-05T11:44:42.361158+00:00"}