{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RZP4UF6475EW23JM27KFJUKSSC","short_pith_number":"pith:RZP4UF64","schema_version":"1.0","canonical_sha256":"8e5fca17dcff496d6d2cd7d454d15290973d9749b4d78d2ef48deacf510281df","source":{"kind":"arxiv","id":"2406.17803","version":1},"attestation_state":"computed","paper":{"title":"Understanding the Role of User Profile in the Personalization of Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Bin Wu, Emine Yilmaz, Hossein A. Rahmani, Varsha Ramineni, Zhengyan Shi","submitted_at":"2024-06-22T14:32:35Z","abstract_excerpt":"Utilizing user profiles to personalize Large Language Models (LLMs) has been shown to enhance the performance on a wide range of tasks. However, the precise role of user profiles and their effect mechanism on LLMs remains unclear. This study first confirms that the effectiveness of user profiles is primarily due to personalization information rather than semantic information. Furthermore, we investigate how user profiles affect the personalization of LLMs. Within the user profile, we reveal that it is the historical personalized response produced or approved by users that plays a pivotal role "},"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":"2406.17803","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-22T14:32:35Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"245ea2d5c686cc0063fa2e6f5650d520d3078623eac68fbf134a0bd4e0fe6408","abstract_canon_sha256":"828bc7107e83dce5f7eb2190f08f44fb6006784db102797af851c1d54ab75db8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:36:50.274781Z","signature_b64":"oKpA/So20khDseYT9mzDX67OiBATq1G+7o8g1vIFab8rtjAlLyFyKk9Ims9vzjoE0JmW5Gbj0JkYOaIJmFV8Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8e5fca17dcff496d6d2cd7d454d15290973d9749b4d78d2ef48deacf510281df","last_reissued_at":"2026-07-05T08:36:50.274207Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:36:50.274207Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Understanding the Role of User Profile in the Personalization of Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Bin Wu, Emine Yilmaz, Hossein A. Rahmani, Varsha Ramineni, Zhengyan Shi","submitted_at":"2024-06-22T14:32:35Z","abstract_excerpt":"Utilizing user profiles to personalize Large Language Models (LLMs) has been shown to enhance the performance on a wide range of tasks. However, the precise role of user profiles and their effect mechanism on LLMs remains unclear. This study first confirms that the effectiveness of user profiles is primarily due to personalization information rather than semantic information. Furthermore, we investigate how user profiles affect the personalization of LLMs. Within the user profile, we reveal that it is the historical personalized response produced or approved by users that plays a pivotal role "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.17803","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/2406.17803/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":"2406.17803","created_at":"2026-07-05T08:36:50.274271+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.17803v1","created_at":"2026-07-05T08:36:50.274271+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.17803","created_at":"2026-07-05T08:36:50.274271+00:00"},{"alias_kind":"pith_short_12","alias_value":"RZP4UF6475EW","created_at":"2026-07-05T08:36:50.274271+00:00"},{"alias_kind":"pith_short_16","alias_value":"RZP4UF6475EW23JM","created_at":"2026-07-05T08:36:50.274271+00:00"},{"alias_kind":"pith_short_8","alias_value":"RZP4UF64","created_at":"2026-07-05T08:36:50.274271+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.09038","citing_title":"Personalization Meets Safety:Mechanisms,Risks,and Mitigations in Personalized LLMs","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27141","citing_title":"VitaBench 2.0: Evaluating Personalized and Proactive Agents in Long-Term User Interactions","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27805","citing_title":"ChildEval: When large language models meet children's personalities","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10013","citing_title":"When Are LLM Inferences Acceptable? User Reactions and Control Preferences for Inferred Personal Information","ref_index":70,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RZP4UF6475EW23JM27KFJUKSSC","json":"https://pith.science/pith/RZP4UF6475EW23JM27KFJUKSSC.json","graph_json":"https://pith.science/api/pith-number/RZP4UF6475EW23JM27KFJUKSSC/graph.json","events_json":"https://pith.science/api/pith-number/RZP4UF6475EW23JM27KFJUKSSC/events.json","paper":"https://pith.science/paper/RZP4UF64"},"agent_actions":{"view_html":"https://pith.science/pith/RZP4UF6475EW23JM27KFJUKSSC","download_json":"https://pith.science/pith/RZP4UF6475EW23JM27KFJUKSSC.json","view_paper":"https://pith.science/paper/RZP4UF64","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.17803&json=true","fetch_graph":"https://pith.science/api/pith-number/RZP4UF6475EW23JM27KFJUKSSC/graph.json","fetch_events":"https://pith.science/api/pith-number/RZP4UF6475EW23JM27KFJUKSSC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RZP4UF6475EW23JM27KFJUKSSC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RZP4UF6475EW23JM27KFJUKSSC/action/storage_attestation","attest_author":"https://pith.science/pith/RZP4UF6475EW23JM27KFJUKSSC/action/author_attestation","sign_citation":"https://pith.science/pith/RZP4UF6475EW23JM27KFJUKSSC/action/citation_signature","submit_replication":"https://pith.science/pith/RZP4UF6475EW23JM27KFJUKSSC/action/replication_record"}},"created_at":"2026-07-05T08:36:50.274271+00:00","updated_at":"2026-07-05T08:36:50.274271+00:00"}