{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3QF4QQYSZYVADAWDFAJACSDLYC","short_pith_number":"pith:3QF4QQYS","schema_version":"1.0","canonical_sha256":"dc0bc84312ce2a0182c3281201486bc0b87b8318eb169f11c9e4a292b30b1831","source":{"kind":"arxiv","id":"2410.12519","version":1},"attestation_state":"computed","paper":{"title":"RosePO: Aligning LLM-based Recommenders with Human Values","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Jiancan Wu, Jiayi Liao, Ruobing Xie, Xiangnan He, Xiang Wang, Xingwu Sun, Yancheng Yuan, Zhanhui Kang","submitted_at":"2024-10-16T12:54:34Z","abstract_excerpt":"Recently, there has been a growing interest in leveraging Large Language Models (LLMs) for recommendation systems, which usually adapt a pre-trained LLM to the recommendation scenario through supervised fine-tuning (SFT). However, both the pre-training and SFT stages fail to explicitly model the comparative relationships of a user's preferences on different items. To construct a \"helpful and harmless\" LLM-based recommender, we propose a general framework -- Recommendation with smoothing personalized Preference Optimization (RosePO), which better aligns with customized human values during the p"},"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":"2410.12519","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-10-16T12:54:34Z","cross_cats_sorted":[],"title_canon_sha256":"4f2588875f8c5229226c5288e54bd9764476409e4b5b2dc8eca8317c4d4d6a63","abstract_canon_sha256":"2c907b6e60ddd710b948b3dd06bc51e53ac88d9910f098738e10f5625c99c223"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:21:30.152225Z","signature_b64":"aKmZzXO1D9oHf9xMqHlTbL386Fve4rMm6+oCBAVHxTJ33fNRdaFI6Ly0P0WjP5tjIkn2Ao/NiIHzgB8gOLmsAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dc0bc84312ce2a0182c3281201486bc0b87b8318eb169f11c9e4a292b30b1831","last_reissued_at":"2026-07-05T09:21:30.151797Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:21:30.151797Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RosePO: Aligning LLM-based Recommenders with Human Values","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Jiancan Wu, Jiayi Liao, Ruobing Xie, Xiangnan He, Xiang Wang, Xingwu Sun, Yancheng Yuan, Zhanhui Kang","submitted_at":"2024-10-16T12:54:34Z","abstract_excerpt":"Recently, there has been a growing interest in leveraging Large Language Models (LLMs) for recommendation systems, which usually adapt a pre-trained LLM to the recommendation scenario through supervised fine-tuning (SFT). However, both the pre-training and SFT stages fail to explicitly model the comparative relationships of a user's preferences on different items. To construct a \"helpful and harmless\" LLM-based recommender, we propose a general framework -- Recommendation with smoothing personalized Preference Optimization (RosePO), which better aligns with customized human values during the p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.12519","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/2410.12519/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":"2410.12519","created_at":"2026-07-05T09:21:30.151855+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.12519v1","created_at":"2026-07-05T09:21:30.151855+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.12519","created_at":"2026-07-05T09:21:30.151855+00:00"},{"alias_kind":"pith_short_12","alias_value":"3QF4QQYSZYVA","created_at":"2026-07-05T09:21:30.151855+00:00"},{"alias_kind":"pith_short_16","alias_value":"3QF4QQYSZYVADAWD","created_at":"2026-07-05T09:21:30.151855+00:00"},{"alias_kind":"pith_short_8","alias_value":"3QF4QQYS","created_at":"2026-07-05T09:21:30.151855+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.00540","citing_title":"Trustworthy Recommendation in the Era of Large Language Models: Opportunities and Challenges","ref_index":132,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16345","citing_title":"Goal-Conditioned Supervised Learning for LLM Fine-Tuning","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2510.27157","citing_title":"A Survey on Generative Recommendation: Data, Model, and Tasks","ref_index":90,"is_internal_anchor":false},{"citing_arxiv_id":"2511.18740","citing_title":"Multimodal Large Language Models with Adaptive Preference Optimization for Sequential Recommendation","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2601.22925","citing_title":"BEAR: Towards Beam-Search-Aware Optimization for Recommendation with Large Language Models","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04559","citing_title":"Beyond Static Best-of-N: Bayesian List-wise Alignment for LLM-based Recommendation","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3QF4QQYSZYVADAWDFAJACSDLYC","json":"https://pith.science/pith/3QF4QQYSZYVADAWDFAJACSDLYC.json","graph_json":"https://pith.science/api/pith-number/3QF4QQYSZYVADAWDFAJACSDLYC/graph.json","events_json":"https://pith.science/api/pith-number/3QF4QQYSZYVADAWDFAJACSDLYC/events.json","paper":"https://pith.science/paper/3QF4QQYS"},"agent_actions":{"view_html":"https://pith.science/pith/3QF4QQYSZYVADAWDFAJACSDLYC","download_json":"https://pith.science/pith/3QF4QQYSZYVADAWDFAJACSDLYC.json","view_paper":"https://pith.science/paper/3QF4QQYS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.12519&json=true","fetch_graph":"https://pith.science/api/pith-number/3QF4QQYSZYVADAWDFAJACSDLYC/graph.json","fetch_events":"https://pith.science/api/pith-number/3QF4QQYSZYVADAWDFAJACSDLYC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3QF4QQYSZYVADAWDFAJACSDLYC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3QF4QQYSZYVADAWDFAJACSDLYC/action/storage_attestation","attest_author":"https://pith.science/pith/3QF4QQYSZYVADAWDFAJACSDLYC/action/author_attestation","sign_citation":"https://pith.science/pith/3QF4QQYSZYVADAWDFAJACSDLYC/action/citation_signature","submit_replication":"https://pith.science/pith/3QF4QQYSZYVADAWDFAJACSDLYC/action/replication_record"}},"created_at":"2026-07-05T09:21:30.151855+00:00","updated_at":"2026-07-05T09:21:30.151855+00:00"}