{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VDDXUNZXZUC2I5H52635TWVXYJ","short_pith_number":"pith:VDDXUNZX","schema_version":"1.0","canonical_sha256":"a8c77a3737cd05a474fdd7b7d9dab7c26e6c5833f86e002883dc5b6879092cc5","source":{"kind":"arxiv","id":"2410.10360","version":3},"attestation_state":"computed","paper":{"title":"Parenting: Optimizing Knowledge Selection of Retrieval-Augmented Language Models with Parameter Decoupling and Tailored Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Junfeng Zhao, Ruizhe Zhang, Runchuan Zhu, Xinke Jiang, Xinyu Ma, Xu Chu, Yasha Wang, Yongxin Xu, Yujie Feng, Yuzhen Xiao","submitted_at":"2024-10-14T10:26:57Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) offers an effective solution to the issues faced by Large Language Models (LLMs) in hallucination generation and knowledge obsolescence by incorporating externally retrieved knowledge. However, existing methods lack effective control mechanisms for integrating internal and external knowledge. Inspired by human cognitive processes, we propose Parenting, a novel framework that decouples, identifies, and purposefully optimizes parameter subspaces related to adherence and robustness. Specifically, Parenting utilizes a key parameter mining method that combines f"},"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":"2410.10360","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-14T10:26:57Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"92aeeff1218837dd95ac25b08cbb3b47ee236daaa75f5a21b0d969dfc9bb359e","abstract_canon_sha256":"60449b27352a5dea0f37e77344a8631f2510b8fb610cff7517f97733f8cc5f12"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:29:02.557262Z","signature_b64":"JlJE8sZq+Hdh/MSOaCU+8+kJNGTeS7/QZ0x7VNn+rG1UJWiJSHVE0V/4m/+ptDXVv6/v4mU6L5HXRIb1OOACAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a8c77a3737cd05a474fdd7b7d9dab7c26e6c5833f86e002883dc5b6879092cc5","last_reissued_at":"2026-07-05T11:29:02.556717Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:29:02.556717Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Parenting: Optimizing Knowledge Selection of Retrieval-Augmented Language Models with Parameter Decoupling and Tailored Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Junfeng Zhao, Ruizhe Zhang, Runchuan Zhu, Xinke Jiang, Xinyu Ma, Xu Chu, Yasha Wang, Yongxin Xu, Yujie Feng, Yuzhen Xiao","submitted_at":"2024-10-14T10:26:57Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) offers an effective solution to the issues faced by Large Language Models (LLMs) in hallucination generation and knowledge obsolescence by incorporating externally retrieved knowledge. However, existing methods lack effective control mechanisms for integrating internal and external knowledge. Inspired by human cognitive processes, we propose Parenting, a novel framework that decouples, identifies, and purposefully optimizes parameter subspaces related to adherence and robustness. Specifically, Parenting utilizes a key parameter mining method that combines f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.10360","kind":"arxiv","version":3},"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/2410.10360/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":"2410.10360","created_at":"2026-07-05T11:29:02.556783+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.10360v3","created_at":"2026-07-05T11:29:02.556783+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.10360","created_at":"2026-07-05T11:29:02.556783+00:00"},{"alias_kind":"pith_short_12","alias_value":"VDDXUNZXZUC2","created_at":"2026-07-05T11:29:02.556783+00:00"},{"alias_kind":"pith_short_16","alias_value":"VDDXUNZXZUC2I5H5","created_at":"2026-07-05T11:29:02.556783+00:00"},{"alias_kind":"pith_short_8","alias_value":"VDDXUNZX","created_at":"2026-07-05T11:29:02.556783+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.05911","citing_title":"GRAIT: Gradient-Driven Refusal-Aware Instruction Tuning for Effective Hallucination Mitigation","ref_index":49,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VDDXUNZXZUC2I5H52635TWVXYJ","json":"https://pith.science/pith/VDDXUNZXZUC2I5H52635TWVXYJ.json","graph_json":"https://pith.science/api/pith-number/VDDXUNZXZUC2I5H52635TWVXYJ/graph.json","events_json":"https://pith.science/api/pith-number/VDDXUNZXZUC2I5H52635TWVXYJ/events.json","paper":"https://pith.science/paper/VDDXUNZX"},"agent_actions":{"view_html":"https://pith.science/pith/VDDXUNZXZUC2I5H52635TWVXYJ","download_json":"https://pith.science/pith/VDDXUNZXZUC2I5H52635TWVXYJ.json","view_paper":"https://pith.science/paper/VDDXUNZX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.10360&json=true","fetch_graph":"https://pith.science/api/pith-number/VDDXUNZXZUC2I5H52635TWVXYJ/graph.json","fetch_events":"https://pith.science/api/pith-number/VDDXUNZXZUC2I5H52635TWVXYJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VDDXUNZXZUC2I5H52635TWVXYJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VDDXUNZXZUC2I5H52635TWVXYJ/action/storage_attestation","attest_author":"https://pith.science/pith/VDDXUNZXZUC2I5H52635TWVXYJ/action/author_attestation","sign_citation":"https://pith.science/pith/VDDXUNZXZUC2I5H52635TWVXYJ/action/citation_signature","submit_replication":"https://pith.science/pith/VDDXUNZXZUC2I5H52635TWVXYJ/action/replication_record"}},"created_at":"2026-07-05T11:29:02.556783+00:00","updated_at":"2026-07-05T11:29:02.556783+00:00"}