{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:BHZTCSRTXGTCICBQ6656JEUEWZ","short_pith_number":"pith:BHZTCSRT","schema_version":"1.0","canonical_sha256":"09f3314a33b9a6240830f7bbe49284b66eb85dae99eb89c8b86197fce56e3370","source":{"kind":"arxiv","id":"2501.04167","version":1},"attestation_state":"computed","paper":{"title":"Reasoning-Enhanced Self-Training for Long-Form Personalized Text Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Alireza Salemi, Cheng Li, Hamed Zamani, Michael Bendersky, Mingyang Zhang, Qiaozhu Mei, Tao Chen, Weize Kong, Zhuowan Li","submitted_at":"2025-01-07T22:29:08Z","abstract_excerpt":"Personalized text generation requires a unique ability of large language models (LLMs) to learn from context that they often do not encounter during their standard training. One way to encourage LLMs to better use personalized context for generating outputs that better align with the user's expectations is to instruct them to reason over the user's past preferences, background knowledge, or writing style. To achieve this, we propose Reasoning-Enhanced Self-Training for Personalized Text Generation (REST-PG), a framework that trains LLMs to reason over personal data during response generation. "},"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":"2501.04167","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-01-07T22:29:08Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"5d616e5d56a695ba18d0450fa65ac9d222aebf4224f2cabbb839bf4b78f01349","abstract_canon_sha256":"5b2c95aaf654e26e89671e6a78f79dd98f337a16e2b70c08393285888164750e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:58:31.189570Z","signature_b64":"9BFvjp7pbluDg8HKSSlq2TAd4kvFQSeElMDpkq71C07DxycC78+RY1mF+ZxRUrs+4nlB67G6/LiCmUIlRYOkDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"09f3314a33b9a6240830f7bbe49284b66eb85dae99eb89c8b86197fce56e3370","last_reissued_at":"2026-07-05T09:58:31.189115Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:58:31.189115Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reasoning-Enhanced Self-Training for Long-Form Personalized Text Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Alireza Salemi, Cheng Li, Hamed Zamani, Michael Bendersky, Mingyang Zhang, Qiaozhu Mei, Tao Chen, Weize Kong, Zhuowan Li","submitted_at":"2025-01-07T22:29:08Z","abstract_excerpt":"Personalized text generation requires a unique ability of large language models (LLMs) to learn from context that they often do not encounter during their standard training. One way to encourage LLMs to better use personalized context for generating outputs that better align with the user's expectations is to instruct them to reason over the user's past preferences, background knowledge, or writing style. To achieve this, we propose Reasoning-Enhanced Self-Training for Personalized Text Generation (REST-PG), a framework that trains LLMs to reason over personal data during response generation. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.04167","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/2501.04167/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":"2501.04167","created_at":"2026-07-05T09:58:31.189177+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.04167v1","created_at":"2026-07-05T09:58:31.189177+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.04167","created_at":"2026-07-05T09:58:31.189177+00:00"},{"alias_kind":"pith_short_12","alias_value":"BHZTCSRTXGTC","created_at":"2026-07-05T09:58:31.189177+00:00"},{"alias_kind":"pith_short_16","alias_value":"BHZTCSRTXGTCICBQ","created_at":"2026-07-05T09:58:31.189177+00:00"},{"alias_kind":"pith_short_8","alias_value":"BHZTCSRT","created_at":"2026-07-05T09:58:31.189177+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.09038","citing_title":"Personalization Meets Safety:Mechanisms,Risks,and Mitigations in Personalized LLMs","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.31545","citing_title":"Preference-Aware Rubric Learning for Personalized Evaluation","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2506.18841","citing_title":"LongWriter-Zero: Mastering Ultra-Long Text Generation via Reinforcement Learning","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2508.10695","citing_title":"Learning from Natural Language Feedback for Personalized Question Answering","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2511.15408","citing_title":"Chinese Short-Form Creative Content Generation via Explanation-Oriented Multi-Objective Optimization","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10530","citing_title":"Personalized Deep Research: A User-Centric Framework, Dataset, and Hybrid Evaluation for Knowledge Discovery","ref_index":33,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BHZTCSRTXGTCICBQ6656JEUEWZ","json":"https://pith.science/pith/BHZTCSRTXGTCICBQ6656JEUEWZ.json","graph_json":"https://pith.science/api/pith-number/BHZTCSRTXGTCICBQ6656JEUEWZ/graph.json","events_json":"https://pith.science/api/pith-number/BHZTCSRTXGTCICBQ6656JEUEWZ/events.json","paper":"https://pith.science/paper/BHZTCSRT"},"agent_actions":{"view_html":"https://pith.science/pith/BHZTCSRTXGTCICBQ6656JEUEWZ","download_json":"https://pith.science/pith/BHZTCSRTXGTCICBQ6656JEUEWZ.json","view_paper":"https://pith.science/paper/BHZTCSRT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.04167&json=true","fetch_graph":"https://pith.science/api/pith-number/BHZTCSRTXGTCICBQ6656JEUEWZ/graph.json","fetch_events":"https://pith.science/api/pith-number/BHZTCSRTXGTCICBQ6656JEUEWZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BHZTCSRTXGTCICBQ6656JEUEWZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BHZTCSRTXGTCICBQ6656JEUEWZ/action/storage_attestation","attest_author":"https://pith.science/pith/BHZTCSRTXGTCICBQ6656JEUEWZ/action/author_attestation","sign_citation":"https://pith.science/pith/BHZTCSRTXGTCICBQ6656JEUEWZ/action/citation_signature","submit_replication":"https://pith.science/pith/BHZTCSRTXGTCICBQ6656JEUEWZ/action/replication_record"}},"created_at":"2026-07-05T09:58:31.189177+00:00","updated_at":"2026-07-05T09:58:31.189177+00:00"}