{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:WQENWIIC6E27IRVYSNKOBMJYTI","short_pith_number":"pith:WQENWIIC","schema_version":"1.0","canonical_sha256":"b408db2102f135f446b89354e0b1389a1c6b0f0cdb36cbe99e5426c4d69b8ce6","source":{"kind":"arxiv","id":"2309.01431","version":2},"attestation_state":"computed","paper":{"title":"Benchmarking Large Language Models in Retrieval-Augmented Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hongyu Lin, Jiawei Chen, Le Sun, Xianpei Han","submitted_at":"2023-09-04T08:28:44Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) is a promising approach for mitigating the hallucination of large language models (LLMs). However, existing research lacks rigorous evaluation of the impact of retrieval-augmented generation on different large language models, which make it challenging to identify the potential bottlenecks in the capabilities of RAG for different LLMs. In this paper, we systematically investigate the impact of Retrieval-Augmented Generation on large language models. We analyze the performance of different large language models in 4 fundamental abilities required for RAG, in"},"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":"2309.01431","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-09-04T08:28:44Z","cross_cats_sorted":[],"title_canon_sha256":"9de341975cd923cdb41399d44dfd00ab8adc536a4a868755ede36bf53dcbc1db","abstract_canon_sha256":"bf028826d8b7c5b9eba4b287a403f4463fd111466d5f79d54ec2b53836cc70cf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:26:16.847154Z","signature_b64":"UYPQWnUWWxHG5DAoC/V2en/CZpK5rgLgLAV2oEBTo1K1tngPomxD5eMGwpNmURDgztN57HW4jxNY4aznuN2VBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b408db2102f135f446b89354e0b1389a1c6b0f0cdb36cbe99e5426c4d69b8ce6","last_reissued_at":"2026-07-05T07:26:16.846644Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:26:16.846644Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Benchmarking Large Language Models in Retrieval-Augmented Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hongyu Lin, Jiawei Chen, Le Sun, Xianpei Han","submitted_at":"2023-09-04T08:28:44Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) is a promising approach for mitigating the hallucination of large language models (LLMs). However, existing research lacks rigorous evaluation of the impact of retrieval-augmented generation on different large language models, which make it challenging to identify the potential bottlenecks in the capabilities of RAG for different LLMs. In this paper, we systematically investigate the impact of Retrieval-Augmented Generation on large language models. We analyze the performance of different large language models in 4 fundamental abilities required for RAG, in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.01431","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/2309.01431/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":"2309.01431","created_at":"2026-07-05T07:26:16.846708+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.01431v2","created_at":"2026-07-05T07:26:16.846708+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.01431","created_at":"2026-07-05T07:26:16.846708+00:00"},{"alias_kind":"pith_short_12","alias_value":"WQENWIIC6E27","created_at":"2026-07-05T07:26:16.846708+00:00"},{"alias_kind":"pith_short_16","alias_value":"WQENWIIC6E27IRVY","created_at":"2026-07-05T07:26:16.846708+00:00"},{"alias_kind":"pith_short_8","alias_value":"WQENWIIC","created_at":"2026-07-05T07:26:16.846708+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26449","citing_title":"ProvenAI: Provenance-Native Traces of Evidence in Generated Answers","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30306","citing_title":"Always-OnAgents:A Survey of Persistent Memory, State, and Governance in LLMAgents","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2312.10997","citing_title":"Retrieval-Augmented Generation for Large Language Models: A Survey","ref_index":167,"is_internal_anchor":false},{"citing_arxiv_id":"2512.14554","citing_title":"VLegal-Bench: Cognitively Grounded Benchmark for Vietnamese Legal Reasoning of Large Language Models","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2401.15391","citing_title":"MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2604.03174","citing_title":"Beyond the Parameters: A Technical Survey of Contextual Enrichment in Large Language Models: From In-Context Prompting to Causal Retrieval-Augmented Generation","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10339","citing_title":"An Annotation Scheme and Classifier for Personal Facts in Dialogue","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WQENWIIC6E27IRVYSNKOBMJYTI","json":"https://pith.science/pith/WQENWIIC6E27IRVYSNKOBMJYTI.json","graph_json":"https://pith.science/api/pith-number/WQENWIIC6E27IRVYSNKOBMJYTI/graph.json","events_json":"https://pith.science/api/pith-number/WQENWIIC6E27IRVYSNKOBMJYTI/events.json","paper":"https://pith.science/paper/WQENWIIC"},"agent_actions":{"view_html":"https://pith.science/pith/WQENWIIC6E27IRVYSNKOBMJYTI","download_json":"https://pith.science/pith/WQENWIIC6E27IRVYSNKOBMJYTI.json","view_paper":"https://pith.science/paper/WQENWIIC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.01431&json=true","fetch_graph":"https://pith.science/api/pith-number/WQENWIIC6E27IRVYSNKOBMJYTI/graph.json","fetch_events":"https://pith.science/api/pith-number/WQENWIIC6E27IRVYSNKOBMJYTI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WQENWIIC6E27IRVYSNKOBMJYTI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WQENWIIC6E27IRVYSNKOBMJYTI/action/storage_attestation","attest_author":"https://pith.science/pith/WQENWIIC6E27IRVYSNKOBMJYTI/action/author_attestation","sign_citation":"https://pith.science/pith/WQENWIIC6E27IRVYSNKOBMJYTI/action/citation_signature","submit_replication":"https://pith.science/pith/WQENWIIC6E27IRVYSNKOBMJYTI/action/replication_record"}},"created_at":"2026-07-05T07:26:16.846708+00:00","updated_at":"2026-07-05T07:26:16.846708+00:00"}