{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:AVH2CKNVFMMO3RBZLVBWPASJPT","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"c00d6fddc11c469524587fea55746f36e93cc066bcef22d56b32769635658b3b","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-06T04:18:58Z","title_canon_sha256":"cfa726f7f7db84bc6644ea0f5ab54f1c631b7e13fb09e4891dd6c61499301ca4"},"schema_version":"1.0","source":{"id":"2402.05133","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.05133","created_at":"2026-07-05T09:45:44Z"},{"alias_kind":"arxiv_version","alias_value":"2402.05133v3","created_at":"2026-07-05T09:45:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.05133","created_at":"2026-07-05T09:45:44Z"},{"alias_kind":"pith_short_12","alias_value":"AVH2CKNVFMMO","created_at":"2026-07-05T09:45:44Z"},{"alias_kind":"pith_short_16","alias_value":"AVH2CKNVFMMO3RBZ","created_at":"2026-07-05T09:45:44Z"},{"alias_kind":"pith_short_8","alias_value":"AVH2CKNV","created_at":"2026-07-05T09:45:44Z"}],"graph_snapshots":[{"event_id":"sha256:59b3444c25a6b6d4c2166f04855e188f95f829dd3aa8b401c000d43ecc1646d7","target":"graph","created_at":"2026-07-05T09:45:44Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2402.05133/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Personalized large language models (LLMs) are designed to tailor responses to individual user preferences. While Reinforcement Learning from Human Feedback (RLHF) is a commonly used framework for aligning LLMs with human preferences, vanilla RLHF assumes that all human preferences share the same distribution, preventing fine-tuned LLMs from generating personalized content when user preferences are diverse. In this work, we propose Personalized-RLHF (P-RLHF), an efficient framework that utilizes a lightweight user model to capture individual user preferences and jointly learns the user model an","authors_text":"Liu Leqi, Ruiyang Zhou, Xinyu Li, Zachary C. Lipton","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-06T04:18:58Z","title":"Personalized Language Modeling from Personalized Human Feedback"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.05133","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:12206b90aac42aa5aa838406d7a36dee8f5d10d69b0648721629bbf98a30d1e5","target":"record","created_at":"2026-07-05T09:45:44Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"c00d6fddc11c469524587fea55746f36e93cc066bcef22d56b32769635658b3b","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-06T04:18:58Z","title_canon_sha256":"cfa726f7f7db84bc6644ea0f5ab54f1c631b7e13fb09e4891dd6c61499301ca4"},"schema_version":"1.0","source":{"id":"2402.05133","kind":"arxiv","version":3}},"canonical_sha256":"054fa129b52b18edc4395d436782497ccd21c7b10b06adabba32e452d4d84401","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"054fa129b52b18edc4395d436782497ccd21c7b10b06adabba32e452d4d84401","first_computed_at":"2026-07-05T09:45:44.082749Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:45:44.082749Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ITsMlvNlPm8ASa8vw7wc89pPlOA7A1MC9wyB0yJEbN3nUu+S2ti4RcHRzFicNIvN1xPjHZ4feL5mZnblnJWQAw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:45:44.083420Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.05133","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:12206b90aac42aa5aa838406d7a36dee8f5d10d69b0648721629bbf98a30d1e5","sha256:59b3444c25a6b6d4c2166f04855e188f95f829dd3aa8b401c000d43ecc1646d7"],"state_sha256":"55b7b601b72209620cfb77373bf8ef5583ed286703829d9ad0226df412d4e14e"}