{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FEYMEEWPCY454OVNXSDCB74K3E","short_pith_number":"pith:FEYMEEWP","schema_version":"1.0","canonical_sha256":"2930c212cf1639de3aadbc8620ff8ad92a1b8f025b2a0a2bd99dcfca7f1b4460","source":{"kind":"arxiv","id":"2402.11129","version":3},"attestation_state":"computed","paper":{"title":"BlendFilter: Advancing Retrieval-Augmented Large Language Models via Query Generation Blending and Knowledge Filtering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chen Luo, Haoming Jiang, Haoyu Wang, Jing Gao, Jinjin Tian, Monica Cheng, Ruirui Li, Tuo Zhao, Xianfeng Tang, Zhengyang Wang","submitted_at":"2024-02-16T23:28:02Z","abstract_excerpt":"Retrieval-augmented Large Language Models (LLMs) offer substantial benefits in enhancing performance across knowledge-intensive scenarios. However, these methods often face challenges with complex inputs and encounter difficulties due to noisy knowledge retrieval, notably hindering model effectiveness. To address this issue, we introduce BlendFilter, a novel approach that elevates retrieval-augmented LLMs by integrating query generation blending with knowledge filtering. BlendFilter proposes the blending process through its query generation method, which integrates both external and internal k"},"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":"2402.11129","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-16T23:28:02Z","cross_cats_sorted":[],"title_canon_sha256":"481af2dc49fe05003012822ec9319abb396cddbaa1f3e40553cfbb3f9b4d35ee","abstract_canon_sha256":"b4c15e4f95b917fae11128e60bcb2d891862f3b46b2ad55f7f6e5cee141b2827"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:21:02.753261Z","signature_b64":"AzX9mYJlyc6UxoZ+lWx1U2Xk46FREA8xygRnIaNo3X7xuN9ODD6H2Ha8YxkG80+cNIYElSXAVBn5iM/MaRUYCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2930c212cf1639de3aadbc8620ff8ad92a1b8f025b2a0a2bd99dcfca7f1b4460","last_reissued_at":"2026-07-05T09:21:02.752750Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:21:02.752750Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BlendFilter: Advancing Retrieval-Augmented Large Language Models via Query Generation Blending and Knowledge Filtering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chen Luo, Haoming Jiang, Haoyu Wang, Jing Gao, Jinjin Tian, Monica Cheng, Ruirui Li, Tuo Zhao, Xianfeng Tang, Zhengyang Wang","submitted_at":"2024-02-16T23:28:02Z","abstract_excerpt":"Retrieval-augmented Large Language Models (LLMs) offer substantial benefits in enhancing performance across knowledge-intensive scenarios. However, these methods often face challenges with complex inputs and encounter difficulties due to noisy knowledge retrieval, notably hindering model effectiveness. To address this issue, we introduce BlendFilter, a novel approach that elevates retrieval-augmented LLMs by integrating query generation blending with knowledge filtering. BlendFilter proposes the blending process through its query generation method, which integrates both external and internal k"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.11129","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/2402.11129/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":"2402.11129","created_at":"2026-07-05T09:21:02.752814+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.11129v3","created_at":"2026-07-05T09:21:02.752814+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.11129","created_at":"2026-07-05T09:21:02.752814+00:00"},{"alias_kind":"pith_short_12","alias_value":"FEYMEEWPCY45","created_at":"2026-07-05T09:21:02.752814+00:00"},{"alias_kind":"pith_short_16","alias_value":"FEYMEEWPCY454OVN","created_at":"2026-07-05T09:21:02.752814+00:00"},{"alias_kind":"pith_short_8","alias_value":"FEYMEEWP","created_at":"2026-07-05T09:21:02.752814+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2404.10981","citing_title":"A Survey on Retrieval-Augmented Text Generation for Large Language Models","ref_index":139,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FEYMEEWPCY454OVNXSDCB74K3E","json":"https://pith.science/pith/FEYMEEWPCY454OVNXSDCB74K3E.json","graph_json":"https://pith.science/api/pith-number/FEYMEEWPCY454OVNXSDCB74K3E/graph.json","events_json":"https://pith.science/api/pith-number/FEYMEEWPCY454OVNXSDCB74K3E/events.json","paper":"https://pith.science/paper/FEYMEEWP"},"agent_actions":{"view_html":"https://pith.science/pith/FEYMEEWPCY454OVNXSDCB74K3E","download_json":"https://pith.science/pith/FEYMEEWPCY454OVNXSDCB74K3E.json","view_paper":"https://pith.science/paper/FEYMEEWP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.11129&json=true","fetch_graph":"https://pith.science/api/pith-number/FEYMEEWPCY454OVNXSDCB74K3E/graph.json","fetch_events":"https://pith.science/api/pith-number/FEYMEEWPCY454OVNXSDCB74K3E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FEYMEEWPCY454OVNXSDCB74K3E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FEYMEEWPCY454OVNXSDCB74K3E/action/storage_attestation","attest_author":"https://pith.science/pith/FEYMEEWPCY454OVNXSDCB74K3E/action/author_attestation","sign_citation":"https://pith.science/pith/FEYMEEWPCY454OVNXSDCB74K3E/action/citation_signature","submit_replication":"https://pith.science/pith/FEYMEEWPCY454OVNXSDCB74K3E/action/replication_record"}},"created_at":"2026-07-05T09:21:02.752814+00:00","updated_at":"2026-07-05T09:21:02.752814+00:00"}