{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:BUJBUW53FSLFTODSOOKNP5FQOB","short_pith_number":"pith:BUJBUW53","schema_version":"1.0","canonical_sha256":"0d121a5bbb2c9659b8727394d7f4b0704eac9a9ed4d1e3757023e69a83ad28c8","source":{"kind":"arxiv","id":"2404.14760","version":2},"attestation_state":"computed","paper":{"title":"Retrieval Augmented Generation for Domain-specific Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"David Seunghyun Yoon, Dewang Sultania, Franck Dernoncourt, Karishma Bagga, Mengjiao Zhang, Sanat Sharma, Trung Bui, Varun Kotte","submitted_at":"2024-04-23T05:51:45Z","abstract_excerpt":"Question answering (QA) has become an important application in the advanced development of large language models. General pre-trained large language models for question-answering are not trained to properly understand the knowledge or terminology for a specific domain, such as finance, healthcare, education, and customer service for a product. To better cater to domain-specific understanding, we build an in-house question-answering system for Adobe products. We propose a novel framework to compile a large question-answer database and develop the approach for retrieval-aware finetuning of a Lar"},"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":"2404.14760","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-23T05:51:45Z","cross_cats_sorted":["cs.AI","cs.IR","cs.LG"],"title_canon_sha256":"a0f28e46fb10d4d8e022675041842d094beb1795249d04457fbec33cf13062f7","abstract_canon_sha256":"3aebe4794071b9588b9181f029776af79f9caa154b96a375c3f6a4a5d76fb42f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:24:42.204399Z","signature_b64":"LZAdh87NGUVC5Hy6BmNcqUWqWpNHZcb45o2wgrmb4c074hyUcehvz2tzl9f5APhcqrfgGD3qSalROHDoiSobAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0d121a5bbb2c9659b8727394d7f4b0704eac9a9ed4d1e3757023e69a83ad28c8","last_reissued_at":"2026-07-05T08:24:42.203977Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:24:42.203977Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Retrieval Augmented Generation for Domain-specific Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"David Seunghyun Yoon, Dewang Sultania, Franck Dernoncourt, Karishma Bagga, Mengjiao Zhang, Sanat Sharma, Trung Bui, Varun Kotte","submitted_at":"2024-04-23T05:51:45Z","abstract_excerpt":"Question answering (QA) has become an important application in the advanced development of large language models. General pre-trained large language models for question-answering are not trained to properly understand the knowledge or terminology for a specific domain, such as finance, healthcare, education, and customer service for a product. To better cater to domain-specific understanding, we build an in-house question-answering system for Adobe products. We propose a novel framework to compile a large question-answer database and develop the approach for retrieval-aware finetuning of a Lar"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.14760","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/2404.14760/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":"2404.14760","created_at":"2026-07-05T08:24:42.204032+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.14760v2","created_at":"2026-07-05T08:24:42.204032+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.14760","created_at":"2026-07-05T08:24:42.204032+00:00"},{"alias_kind":"pith_short_12","alias_value":"BUJBUW53FSLF","created_at":"2026-07-05T08:24:42.204032+00:00"},{"alias_kind":"pith_short_16","alias_value":"BUJBUW53FSLFTODS","created_at":"2026-07-05T08:24:42.204032+00:00"},{"alias_kind":"pith_short_8","alias_value":"BUJBUW53","created_at":"2026-07-05T08:24:42.204032+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.18796","citing_title":"UCCI: Calibrated Uncertainty for Cost-Optimal LLM Cascade Routing","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18812","citing_title":"PASC: Pipeline-Aware Conformal Prediction with Joint Coverage Guarantees for Multi-Stage NLP and LLM Pipelines","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10745","citing_title":"How You Ask Matters! Adaptive RAG Robustness to Query Variations","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BUJBUW53FSLFTODSOOKNP5FQOB","json":"https://pith.science/pith/BUJBUW53FSLFTODSOOKNP5FQOB.json","graph_json":"https://pith.science/api/pith-number/BUJBUW53FSLFTODSOOKNP5FQOB/graph.json","events_json":"https://pith.science/api/pith-number/BUJBUW53FSLFTODSOOKNP5FQOB/events.json","paper":"https://pith.science/paper/BUJBUW53"},"agent_actions":{"view_html":"https://pith.science/pith/BUJBUW53FSLFTODSOOKNP5FQOB","download_json":"https://pith.science/pith/BUJBUW53FSLFTODSOOKNP5FQOB.json","view_paper":"https://pith.science/paper/BUJBUW53","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.14760&json=true","fetch_graph":"https://pith.science/api/pith-number/BUJBUW53FSLFTODSOOKNP5FQOB/graph.json","fetch_events":"https://pith.science/api/pith-number/BUJBUW53FSLFTODSOOKNP5FQOB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BUJBUW53FSLFTODSOOKNP5FQOB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BUJBUW53FSLFTODSOOKNP5FQOB/action/storage_attestation","attest_author":"https://pith.science/pith/BUJBUW53FSLFTODSOOKNP5FQOB/action/author_attestation","sign_citation":"https://pith.science/pith/BUJBUW53FSLFTODSOOKNP5FQOB/action/citation_signature","submit_replication":"https://pith.science/pith/BUJBUW53FSLFTODSOOKNP5FQOB/action/replication_record"}},"created_at":"2026-07-05T08:24:42.204032+00:00","updated_at":"2026-07-05T08:24:42.204032+00:00"}