{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:2XWK37I5SMD5GOZXY2HBZV6O4W","short_pith_number":"pith:2XWK37I5","schema_version":"1.0","canonical_sha256":"d5ecadfd1d9307d33b37c68e1cd7cee586299dcfbaa25c055ed319e75e24250c","source":{"kind":"arxiv","id":"2502.06148","version":1},"attestation_state":"computed","paper":{"title":"Optimizing Knowledge Integration in Retrieval-Augmented Generation with Self-Selection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Fengbin Zhu, Fuli Feng, Haoyan Liu, Tat-Seng Chua, Tong Ye, Yan Weng","submitted_at":"2025-02-10T04:29:36Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG), which integrates external knowledge into Large Language Models (LLMs), has proven effective in enabling LLMs to produce more accurate and reliable responses. However, it remains a significant challenge how to effectively integrate external retrieved knowledge with internal parametric knowledge in LLMs. In this work, we propose a novel Self-Selection RAG framework, where the LLM is made to select from pairwise responses generated with internal parametric knowledge solely and with external retrieved knowledge together to achieve enhanced accuracy. To this en"},"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":"2502.06148","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-10T04:29:36Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"44fdb9edba5be5c689994c78838ff3d11f356b722f787706bac931e8200b2386","abstract_canon_sha256":"1cc76b0dcafd7eb2900b070aa484b29fd32ed6d16df413c5ec916800a6ee8203"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:11:48.371073Z","signature_b64":"1HyQqkV+gN8hiJfiB2nENfFg/nDppsvQvI2uGw0LkykbiZSPOPc+mLxgAQ23SlRESrIwDifD2JESzyRF4zSoDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d5ecadfd1d9307d33b37c68e1cd7cee586299dcfbaa25c055ed319e75e24250c","last_reissued_at":"2026-07-05T10:11:48.370635Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:11:48.370635Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Optimizing Knowledge Integration in Retrieval-Augmented Generation with Self-Selection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Fengbin Zhu, Fuli Feng, Haoyan Liu, Tat-Seng Chua, Tong Ye, Yan Weng","submitted_at":"2025-02-10T04:29:36Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG), which integrates external knowledge into Large Language Models (LLMs), has proven effective in enabling LLMs to produce more accurate and reliable responses. However, it remains a significant challenge how to effectively integrate external retrieved knowledge with internal parametric knowledge in LLMs. In this work, we propose a novel Self-Selection RAG framework, where the LLM is made to select from pairwise responses generated with internal parametric knowledge solely and with external retrieved knowledge together to achieve enhanced accuracy. To this en"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.06148","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/2502.06148/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":"2502.06148","created_at":"2026-07-05T10:11:48.370690+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.06148v1","created_at":"2026-07-05T10:11:48.370690+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.06148","created_at":"2026-07-05T10:11:48.370690+00:00"},{"alias_kind":"pith_short_12","alias_value":"2XWK37I5SMD5","created_at":"2026-07-05T10:11:48.370690+00:00"},{"alias_kind":"pith_short_16","alias_value":"2XWK37I5SMD5GOZX","created_at":"2026-07-05T10:11:48.370690+00:00"},{"alias_kind":"pith_short_8","alias_value":"2XWK37I5","created_at":"2026-07-05T10:11:48.370690+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2XWK37I5SMD5GOZXY2HBZV6O4W","json":"https://pith.science/pith/2XWK37I5SMD5GOZXY2HBZV6O4W.json","graph_json":"https://pith.science/api/pith-number/2XWK37I5SMD5GOZXY2HBZV6O4W/graph.json","events_json":"https://pith.science/api/pith-number/2XWK37I5SMD5GOZXY2HBZV6O4W/events.json","paper":"https://pith.science/paper/2XWK37I5"},"agent_actions":{"view_html":"https://pith.science/pith/2XWK37I5SMD5GOZXY2HBZV6O4W","download_json":"https://pith.science/pith/2XWK37I5SMD5GOZXY2HBZV6O4W.json","view_paper":"https://pith.science/paper/2XWK37I5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.06148&json=true","fetch_graph":"https://pith.science/api/pith-number/2XWK37I5SMD5GOZXY2HBZV6O4W/graph.json","fetch_events":"https://pith.science/api/pith-number/2XWK37I5SMD5GOZXY2HBZV6O4W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2XWK37I5SMD5GOZXY2HBZV6O4W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2XWK37I5SMD5GOZXY2HBZV6O4W/action/storage_attestation","attest_author":"https://pith.science/pith/2XWK37I5SMD5GOZXY2HBZV6O4W/action/author_attestation","sign_citation":"https://pith.science/pith/2XWK37I5SMD5GOZXY2HBZV6O4W/action/citation_signature","submit_replication":"https://pith.science/pith/2XWK37I5SMD5GOZXY2HBZV6O4W/action/replication_record"}},"created_at":"2026-07-05T10:11:48.370690+00:00","updated_at":"2026-07-05T10:11:48.370690+00:00"}