{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:NTBQ7F3OPKRPBJFEL2TJ42IZLK","short_pith_number":"pith:NTBQ7F3O","schema_version":"1.0","canonical_sha256":"6cc30f976e7aa2f0a4a45ea69e69195a88994b8380b66dea9070943ff6810c9d","source":{"kind":"arxiv","id":"2308.07968","version":1},"attestation_state":"computed","paper":{"title":"Teach LLMs to Personalize -- An Approach inspired by Writing Education","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Cheng Li, Michael Bendersky, Mingyang Zhang, Qiaozhu Mei, Spurthi Amba Hombaiah, Yaqing Wang, Yi Liang","submitted_at":"2023-08-15T18:06:23Z","abstract_excerpt":"Personalized text generation is an emerging research area that has attracted much attention in recent years. Most studies in this direction focus on a particular domain by designing bespoke features or models. In this work, we propose a general approach for personalized text generation using large language models (LLMs). Inspired by the practice of writing education, we develop a multistage and multitask framework to teach LLMs for personalized generation. In writing instruction, the task of writing from sources is often decomposed into multiple steps that involve finding, evaluating, summariz"},"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":"2308.07968","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-08-15T18:06:23Z","cross_cats_sorted":[],"title_canon_sha256":"e54f9515f0d293b3b66463d0ef5ee0ac957132acf194a7ff643cd6ae7e22b046","abstract_canon_sha256":"c5239d0d3fb5d3bd49ca5609eb2acd1f30465384d165c95b72ef22faad180e97"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:41:52.324366Z","signature_b64":"MAO6Nu8ShH151usRCN04NYE2VX5YqMkO+OIauOHvgACMjVRn4zPxP5AtSpAaPCsLGxxDFoE9iZnSLA2B03aqBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6cc30f976e7aa2f0a4a45ea69e69195a88994b8380b66dea9070943ff6810c9d","last_reissued_at":"2026-07-05T06:41:52.323920Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:41:52.323920Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Teach LLMs to Personalize -- An Approach inspired by Writing Education","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Cheng Li, Michael Bendersky, Mingyang Zhang, Qiaozhu Mei, Spurthi Amba Hombaiah, Yaqing Wang, Yi Liang","submitted_at":"2023-08-15T18:06:23Z","abstract_excerpt":"Personalized text generation is an emerging research area that has attracted much attention in recent years. Most studies in this direction focus on a particular domain by designing bespoke features or models. In this work, we propose a general approach for personalized text generation using large language models (LLMs). Inspired by the practice of writing education, we develop a multistage and multitask framework to teach LLMs for personalized generation. In writing instruction, the task of writing from sources is often decomposed into multiple steps that involve finding, evaluating, summariz"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.07968","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/2308.07968/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":"2308.07968","created_at":"2026-07-05T06:41:52.323980+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.07968v1","created_at":"2026-07-05T06:41:52.323980+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.07968","created_at":"2026-07-05T06:41:52.323980+00:00"},{"alias_kind":"pith_short_12","alias_value":"NTBQ7F3OPKRP","created_at":"2026-07-05T06:41:52.323980+00:00"},{"alias_kind":"pith_short_16","alias_value":"NTBQ7F3OPKRPBJFE","created_at":"2026-07-05T06:41:52.323980+00:00"},{"alias_kind":"pith_short_8","alias_value":"NTBQ7F3O","created_at":"2026-07-05T06:41:52.323980+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.01485","citing_title":"CoPersona: Collaborative Persona Graphs for Robust LLM Personalization","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04547","citing_title":"Beyond Retrieval: Learning Compact User Representations for Scalable LLM Personalization","ref_index":103,"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":26,"is_internal_anchor":false},{"citing_arxiv_id":"2508.10695","citing_title":"Learning from Natural Language Feedback for Personalized Question Answering","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NTBQ7F3OPKRPBJFEL2TJ42IZLK","json":"https://pith.science/pith/NTBQ7F3OPKRPBJFEL2TJ42IZLK.json","graph_json":"https://pith.science/api/pith-number/NTBQ7F3OPKRPBJFEL2TJ42IZLK/graph.json","events_json":"https://pith.science/api/pith-number/NTBQ7F3OPKRPBJFEL2TJ42IZLK/events.json","paper":"https://pith.science/paper/NTBQ7F3O"},"agent_actions":{"view_html":"https://pith.science/pith/NTBQ7F3OPKRPBJFEL2TJ42IZLK","download_json":"https://pith.science/pith/NTBQ7F3OPKRPBJFEL2TJ42IZLK.json","view_paper":"https://pith.science/paper/NTBQ7F3O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.07968&json=true","fetch_graph":"https://pith.science/api/pith-number/NTBQ7F3OPKRPBJFEL2TJ42IZLK/graph.json","fetch_events":"https://pith.science/api/pith-number/NTBQ7F3OPKRPBJFEL2TJ42IZLK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NTBQ7F3OPKRPBJFEL2TJ42IZLK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NTBQ7F3OPKRPBJFEL2TJ42IZLK/action/storage_attestation","attest_author":"https://pith.science/pith/NTBQ7F3OPKRPBJFEL2TJ42IZLK/action/author_attestation","sign_citation":"https://pith.science/pith/NTBQ7F3OPKRPBJFEL2TJ42IZLK/action/citation_signature","submit_replication":"https://pith.science/pith/NTBQ7F3OPKRPBJFEL2TJ42IZLK/action/replication_record"}},"created_at":"2026-07-05T06:41:52.323980+00:00","updated_at":"2026-07-05T06:41:52.323980+00:00"}