{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:A6GEO2YGWK5T2NOODSVODFF3XM","short_pith_number":"pith:A6GEO2YG","schema_version":"1.0","canonical_sha256":"078c476b06b2bb3d35ce1caae194bbbb0125ba7da96575dd5fd19d62df6313de","source":{"kind":"arxiv","id":"2403.10446","version":1},"attestation_state":"computed","paper":{"title":"Enhancing LLM Factual Accuracy with RAG to Counter Hallucinations: A Case Study on Domain-Specific Queries in Private Knowledge-Bases","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Jiarui Li, Ye Yuan, Zehua Zhang","submitted_at":"2024-03-15T16:30:14Z","abstract_excerpt":"We proposed an end-to-end system design towards utilizing Retrieval Augmented Generation (RAG) to improve the factual accuracy of Large Language Models (LLMs) for domain-specific and time-sensitive queries related to private knowledge-bases. Our system integrates RAG pipeline with upstream datasets processing and downstream performance evaluation. Addressing the challenge of LLM hallucinations, we finetune models with a curated dataset which originates from CMU's extensive resources and annotated with the teacher model. Our experiments demonstrate the system's effectiveness in generating more "},"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":"2403.10446","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-15T16:30:14Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c704dff9217d47d9f5b79ce301482ed0716e5429f42d87b3fa19b87001fb0ff0","abstract_canon_sha256":"7508cacce238b841d04143d59f2a503568c5590584cc530f53935444e1bcddad"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:56:41.632511Z","signature_b64":"YYR/5L233idNZa55wJxCoSgdAS9I+TPMf5ozKBXQ++EmIesXC2Lc33Klk72Bhp2f7yt5+TP+sqhnMFDLOlmNDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"078c476b06b2bb3d35ce1caae194bbbb0125ba7da96575dd5fd19d62df6313de","last_reissued_at":"2026-07-05T07:56:41.632020Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:56:41.632020Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing LLM Factual Accuracy with RAG to Counter Hallucinations: A Case Study on Domain-Specific Queries in Private Knowledge-Bases","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Jiarui Li, Ye Yuan, Zehua Zhang","submitted_at":"2024-03-15T16:30:14Z","abstract_excerpt":"We proposed an end-to-end system design towards utilizing Retrieval Augmented Generation (RAG) to improve the factual accuracy of Large Language Models (LLMs) for domain-specific and time-sensitive queries related to private knowledge-bases. Our system integrates RAG pipeline with upstream datasets processing and downstream performance evaluation. Addressing the challenge of LLM hallucinations, we finetune models with a curated dataset which originates from CMU's extensive resources and annotated with the teacher model. Our experiments demonstrate the system's effectiveness in generating more "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.10446","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/2403.10446/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":"2403.10446","created_at":"2026-07-05T07:56:41.632072+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.10446v1","created_at":"2026-07-05T07:56:41.632072+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.10446","created_at":"2026-07-05T07:56:41.632072+00:00"},{"alias_kind":"pith_short_12","alias_value":"A6GEO2YGWK5T","created_at":"2026-07-05T07:56:41.632072+00:00"},{"alias_kind":"pith_short_16","alias_value":"A6GEO2YGWK5T2NOO","created_at":"2026-07-05T07:56:41.632072+00:00"},{"alias_kind":"pith_short_8","alias_value":"A6GEO2YG","created_at":"2026-07-05T07:56:41.632072+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.16347","citing_title":"HPC-LLM: Practical Domain Adaptation and Retrieval-Augmented Generation for HPC Support","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18806","citing_title":"Towards FairRAG: Preventing Representational Harm in Retrieval-Augmented Generation by Enforcing Fair Exposure at Retrieval Time","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2402.19473","citing_title":"Retrieval-Augmented Generation for AI-Generated Content: A Survey","ref_index":158,"is_internal_anchor":false},{"citing_arxiv_id":"2603.25412","citing_title":"Beyond Content Safety: Real-Time Monitoring for Reasoning Vulnerabilities in Large Language Models","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19776","citing_title":"Development and Preliminary Evaluation of a Domain-Specific Large Language Model for Tuberculosis Care in South Africa","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18424","citing_title":"Context-Aware Search and Retrieval Under Token Erasure","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/A6GEO2YGWK5T2NOODSVODFF3XM","json":"https://pith.science/pith/A6GEO2YGWK5T2NOODSVODFF3XM.json","graph_json":"https://pith.science/api/pith-number/A6GEO2YGWK5T2NOODSVODFF3XM/graph.json","events_json":"https://pith.science/api/pith-number/A6GEO2YGWK5T2NOODSVODFF3XM/events.json","paper":"https://pith.science/paper/A6GEO2YG"},"agent_actions":{"view_html":"https://pith.science/pith/A6GEO2YGWK5T2NOODSVODFF3XM","download_json":"https://pith.science/pith/A6GEO2YGWK5T2NOODSVODFF3XM.json","view_paper":"https://pith.science/paper/A6GEO2YG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.10446&json=true","fetch_graph":"https://pith.science/api/pith-number/A6GEO2YGWK5T2NOODSVODFF3XM/graph.json","fetch_events":"https://pith.science/api/pith-number/A6GEO2YGWK5T2NOODSVODFF3XM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A6GEO2YGWK5T2NOODSVODFF3XM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A6GEO2YGWK5T2NOODSVODFF3XM/action/storage_attestation","attest_author":"https://pith.science/pith/A6GEO2YGWK5T2NOODSVODFF3XM/action/author_attestation","sign_citation":"https://pith.science/pith/A6GEO2YGWK5T2NOODSVODFF3XM/action/citation_signature","submit_replication":"https://pith.science/pith/A6GEO2YGWK5T2NOODSVODFF3XM/action/replication_record"}},"created_at":"2026-07-05T07:56:41.632072+00:00","updated_at":"2026-07-05T07:56:41.632072+00:00"}