{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:UIQCMOCEZBS77J4VS5E2IXU4M2","short_pith_number":"pith:UIQCMOCE","schema_version":"1.0","canonical_sha256":"a220263844c865ffa7959749a45e9c66b0de40a1aa0a59c9c9a30b8ae9837dbf","source":{"kind":"arxiv","id":"2501.02173","version":2},"attestation_state":"computed","paper":{"title":"The Efficiency vs. Accuracy Trade-off: Optimizing RAG-Enhanced LLM Recommender Systems Using Multi-Head Early Exit","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.IR","authors_text":"Bo Long, Buyun Zhang, Hengrui Gu, Huayu Li, Huixue Zhou, Jiyan Yang, Kaixiong Zhou, Liang Luo, Mingfu Liang, Piyush Chawla, Rui Zhang, Srinivas Govindan, Tianlong Chen, Wen-yen Chen, Xiangfei Meng, Xi Liu, Yiping Han, Yongkang Xiao","submitted_at":"2025-01-04T03:26:46Z","abstract_excerpt":"The deployment of Large Language Models (LLMs) in recommender systems for predicting Click-Through Rates (CTR) necessitates a delicate balance between computational efficiency and predictive accuracy. This paper presents an optimization framework that combines Retrieval-Augmented Generation (RAG) with an innovative multi-head early exit architecture to concurrently enhance both aspects. By integrating Graph Convolutional Networks (GCNs) as efficient retrieval mechanisms, we are able to significantly reduce data retrieval times while maintaining high model performance. The early exit strategy e"},"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":"2501.02173","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-01-04T03:26:46Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e1e069a3aab2a0d6c5ffadd8c13e8ee384278fccd073988dfddbf8dd30ac8c8a","abstract_canon_sha256":"d609d20fca34a416416d056ffc32c55a041249dfac1787d3ab7282c66e65d3d1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-03T01:05:43.340685Z","signature_b64":"HpYd4GtRQ6FgsNE3wxEQlVg2wsxA/vrx3uTN4aqZOR0MzBAoqDduR1eb6345Il/1L1LMovfYxtgqcNZa+QBMAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a220263844c865ffa7959749a45e9c66b0de40a1aa0a59c9c9a30b8ae9837dbf","last_reissued_at":"2026-06-03T01:05:43.340171Z","signature_status":"signed_v1","first_computed_at":"2026-06-03T01:05:43.340171Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Efficiency vs. Accuracy Trade-off: Optimizing RAG-Enhanced LLM Recommender Systems Using Multi-Head Early Exit","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.IR","authors_text":"Bo Long, Buyun Zhang, Hengrui Gu, Huayu Li, Huixue Zhou, Jiyan Yang, Kaixiong Zhou, Liang Luo, Mingfu Liang, Piyush Chawla, Rui Zhang, Srinivas Govindan, Tianlong Chen, Wen-yen Chen, Xiangfei Meng, Xi Liu, Yiping Han, Yongkang Xiao","submitted_at":"2025-01-04T03:26:46Z","abstract_excerpt":"The deployment of Large Language Models (LLMs) in recommender systems for predicting Click-Through Rates (CTR) necessitates a delicate balance between computational efficiency and predictive accuracy. This paper presents an optimization framework that combines Retrieval-Augmented Generation (RAG) with an innovative multi-head early exit architecture to concurrently enhance both aspects. By integrating Graph Convolutional Networks (GCNs) as efficient retrieval mechanisms, we are able to significantly reduce data retrieval times while maintaining high model performance. The early exit strategy e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.02173","kind":"arxiv","version":2},"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/2501.02173/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":"2501.02173","created_at":"2026-06-03T01:05:43.340229+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.02173v2","created_at":"2026-06-03T01:05:43.340229+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.02173","created_at":"2026-06-03T01:05:43.340229+00:00"},{"alias_kind":"pith_short_12","alias_value":"UIQCMOCEZBS7","created_at":"2026-06-03T01:05:43.340229+00:00"},{"alias_kind":"pith_short_16","alias_value":"UIQCMOCEZBS77J4V","created_at":"2026-06-03T01:05:43.340229+00:00"},{"alias_kind":"pith_short_8","alias_value":"UIQCMOCE","created_at":"2026-06-03T01:05:43.340229+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/UIQCMOCEZBS77J4VS5E2IXU4M2","json":"https://pith.science/pith/UIQCMOCEZBS77J4VS5E2IXU4M2.json","graph_json":"https://pith.science/api/pith-number/UIQCMOCEZBS77J4VS5E2IXU4M2/graph.json","events_json":"https://pith.science/api/pith-number/UIQCMOCEZBS77J4VS5E2IXU4M2/events.json","paper":"https://pith.science/paper/UIQCMOCE"},"agent_actions":{"view_html":"https://pith.science/pith/UIQCMOCEZBS77J4VS5E2IXU4M2","download_json":"https://pith.science/pith/UIQCMOCEZBS77J4VS5E2IXU4M2.json","view_paper":"https://pith.science/paper/UIQCMOCE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.02173&json=true","fetch_graph":"https://pith.science/api/pith-number/UIQCMOCEZBS77J4VS5E2IXU4M2/graph.json","fetch_events":"https://pith.science/api/pith-number/UIQCMOCEZBS77J4VS5E2IXU4M2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UIQCMOCEZBS77J4VS5E2IXU4M2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UIQCMOCEZBS77J4VS5E2IXU4M2/action/storage_attestation","attest_author":"https://pith.science/pith/UIQCMOCEZBS77J4VS5E2IXU4M2/action/author_attestation","sign_citation":"https://pith.science/pith/UIQCMOCEZBS77J4VS5E2IXU4M2/action/citation_signature","submit_replication":"https://pith.science/pith/UIQCMOCEZBS77J4VS5E2IXU4M2/action/replication_record"}},"created_at":"2026-06-03T01:05:43.340229+00:00","updated_at":"2026-06-03T01:05:43.340229+00:00"}