{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PJWNFSTPCERJSH4EDGDBF53EVH","short_pith_number":"pith:PJWNFSTP","schema_version":"1.0","canonical_sha256":"7a6cd2ca6f1122991f84198612f764a9c5c6ce25470889db7e9ae863bcf31537","source":{"kind":"arxiv","id":"2404.11792","version":2},"attestation_state":"computed","paper":{"title":"Enhancing Q&A with Domain-Specific Fine-Tuning and Iterative Reasoning: A Comparative Study","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Anh Hai Ha, Anthony Annunziata, Chanh Le, Christopher Nguyen, Hong An Phan, Quynh Le, Sang Dinh, Shruti Raghavan, Vinh Luong, Zooey Nguyen","submitted_at":"2024-04-17T23:00:03Z","abstract_excerpt":"This paper investigates the impact of domain-specific model fine-tuning and of reasoning mechanisms on the performance of question-answering (Q&A) systems powered by large language models (LLMs) and Retrieval-Augmented Generation (RAG). Using the FinanceBench SEC financial filings dataset, we observe that, for RAG, combining a fine-tuned embedding model with a fine-tuned LLM achieves better accuracy than generic models, with relatively greater gains attributable to fine-tuned embedding models. Additionally, employing reasoning iterations on top of RAG delivers an even bigger jump in performanc"},"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":"2404.11792","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-04-17T23:00:03Z","cross_cats_sorted":[],"title_canon_sha256":"6a742d352d6cab254e697cede365fc0f2be62cafc1b26ae411d9bbb9d5ca3d07","abstract_canon_sha256":"68143c1c8027e9d28e44637dde32cbef5e40c88d347a01f0a0f08e0970dc6462"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:10:26.933014Z","signature_b64":"KRrBRC0bgsshCT8PMXjapUoqoNQqMZDEps1QDx7r7pDURwC9d6+1KlqkAcgoM5n56HXcQXH1qnH8yW7b7co9DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7a6cd2ca6f1122991f84198612f764a9c5c6ce25470889db7e9ae863bcf31537","last_reissued_at":"2026-07-05T08:10:26.932572Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:10:26.932572Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing Q&A with Domain-Specific Fine-Tuning and Iterative Reasoning: A Comparative Study","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Anh Hai Ha, Anthony Annunziata, Chanh Le, Christopher Nguyen, Hong An Phan, Quynh Le, Sang Dinh, Shruti Raghavan, Vinh Luong, Zooey Nguyen","submitted_at":"2024-04-17T23:00:03Z","abstract_excerpt":"This paper investigates the impact of domain-specific model fine-tuning and of reasoning mechanisms on the performance of question-answering (Q&A) systems powered by large language models (LLMs) and Retrieval-Augmented Generation (RAG). Using the FinanceBench SEC financial filings dataset, we observe that, for RAG, combining a fine-tuned embedding model with a fine-tuned LLM achieves better accuracy than generic models, with relatively greater gains attributable to fine-tuned embedding models. Additionally, employing reasoning iterations on top of RAG delivers an even bigger jump in performanc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.11792","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/2404.11792/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":"2404.11792","created_at":"2026-07-05T08:10:26.932628+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.11792v2","created_at":"2026-07-05T08:10:26.932628+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.11792","created_at":"2026-07-05T08:10:26.932628+00:00"},{"alias_kind":"pith_short_12","alias_value":"PJWNFSTPCERJ","created_at":"2026-07-05T08:10:26.932628+00:00"},{"alias_kind":"pith_short_16","alias_value":"PJWNFSTPCERJSH4E","created_at":"2026-07-05T08:10:26.932628+00:00"},{"alias_kind":"pith_short_8","alias_value":"PJWNFSTP","created_at":"2026-07-05T08:10:26.932628+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.25030","citing_title":"MimirRAG: A Multi-Agent RAG Framework for Financial Data Retrieval with Metadata Integration","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16347","citing_title":"HPC-LLM: Practical Domain Adaptation and Retrieval-Augmented Generation for HPC Support","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09533","citing_title":"Assessment of RAG and Fine-Tuning for Industrial Question-Answering-Applications","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PJWNFSTPCERJSH4EDGDBF53EVH","json":"https://pith.science/pith/PJWNFSTPCERJSH4EDGDBF53EVH.json","graph_json":"https://pith.science/api/pith-number/PJWNFSTPCERJSH4EDGDBF53EVH/graph.json","events_json":"https://pith.science/api/pith-number/PJWNFSTPCERJSH4EDGDBF53EVH/events.json","paper":"https://pith.science/paper/PJWNFSTP"},"agent_actions":{"view_html":"https://pith.science/pith/PJWNFSTPCERJSH4EDGDBF53EVH","download_json":"https://pith.science/pith/PJWNFSTPCERJSH4EDGDBF53EVH.json","view_paper":"https://pith.science/paper/PJWNFSTP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.11792&json=true","fetch_graph":"https://pith.science/api/pith-number/PJWNFSTPCERJSH4EDGDBF53EVH/graph.json","fetch_events":"https://pith.science/api/pith-number/PJWNFSTPCERJSH4EDGDBF53EVH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PJWNFSTPCERJSH4EDGDBF53EVH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PJWNFSTPCERJSH4EDGDBF53EVH/action/storage_attestation","attest_author":"https://pith.science/pith/PJWNFSTPCERJSH4EDGDBF53EVH/action/author_attestation","sign_citation":"https://pith.science/pith/PJWNFSTPCERJSH4EDGDBF53EVH/action/citation_signature","submit_replication":"https://pith.science/pith/PJWNFSTPCERJSH4EDGDBF53EVH/action/replication_record"}},"created_at":"2026-07-05T08:10:26.932628+00:00","updated_at":"2026-07-05T08:10:26.932628+00:00"}