{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XOFMGYIBTDWFYSAXQESJJNFI6X","short_pith_number":"pith:XOFMGYIB","schema_version":"1.0","canonical_sha256":"bb8ac3610198ec5c4817812494b4a8f5e5b0dd5ab6dfb2c9f8fb36c8dd024ed8","source":{"kind":"arxiv","id":"2410.17952","version":2},"attestation_state":"computed","paper":{"title":"SimRAG: Self-Improving Retrieval-Augmented Generation for Adapting Large Language Models to Specialized Domains","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Carl Yang, Chen Luo, Hui Liu, Joyce C. Ho, Qi He, Ran Xu, Sreyashi Nag, Xianfeng Tang, Yang Li, Yaochen Xie, Zhenwei Dai","submitted_at":"2024-10-23T15:24:16Z","abstract_excerpt":"Retrieval-augmented generation (RAG) enhances the question-answering (QA) abilities of large language models (LLMs) by integrating external knowledge. However, adapting general-purpose RAG systems to specialized fields such as science and medicine poses unique challenges due to distribution shifts and limited access to domain-specific data. To tackle this, we propose SimRAG, a self-training approach that equips the LLM with joint capabilities of question answering and question generation for domain adaptation. Our method first fine-tunes the LLM on instruction-following, question-answering, an"},"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":"2410.17952","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-23T15:24:16Z","cross_cats_sorted":["cs.AI","cs.IR","cs.LG"],"title_canon_sha256":"0d11bd6ce341cf6b5fcdd719f5bfca0984d9d156d10e40d415dd8951f72f1874","abstract_canon_sha256":"28b9192b3ad33c2b6e0852859a499de196cf7932df7a72e83022f7431219e4d1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:05:13.929374Z","signature_b64":"Jm0Gb2L6mdWJ8Kf8m8b7xsVNRBryaxHZyTE/bHP22XlZ+hiA5SzVFGU/szHPjS0X0dUn6LAHwk9lTIYVzNotDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bb8ac3610198ec5c4817812494b4a8f5e5b0dd5ab6dfb2c9f8fb36c8dd024ed8","last_reissued_at":"2026-07-05T10:05:13.928752Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:05:13.928752Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SimRAG: Self-Improving Retrieval-Augmented Generation for Adapting Large Language Models to Specialized Domains","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Carl Yang, Chen Luo, Hui Liu, Joyce C. Ho, Qi He, Ran Xu, Sreyashi Nag, Xianfeng Tang, Yang Li, Yaochen Xie, Zhenwei Dai","submitted_at":"2024-10-23T15:24:16Z","abstract_excerpt":"Retrieval-augmented generation (RAG) enhances the question-answering (QA) abilities of large language models (LLMs) by integrating external knowledge. However, adapting general-purpose RAG systems to specialized fields such as science and medicine poses unique challenges due to distribution shifts and limited access to domain-specific data. To tackle this, we propose SimRAG, a self-training approach that equips the LLM with joint capabilities of question answering and question generation for domain adaptation. Our method first fine-tunes the LLM on instruction-following, question-answering, an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.17952","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/2410.17952/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":"2410.17952","created_at":"2026-07-05T10:05:13.928841+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.17952v2","created_at":"2026-07-05T10:05:13.928841+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.17952","created_at":"2026-07-05T10:05:13.928841+00:00"},{"alias_kind":"pith_short_12","alias_value":"XOFMGYIBTDWF","created_at":"2026-07-05T10:05:13.928841+00:00"},{"alias_kind":"pith_short_16","alias_value":"XOFMGYIBTDWFYSAX","created_at":"2026-07-05T10:05:13.928841+00:00"},{"alias_kind":"pith_short_8","alias_value":"XOFMGYIB","created_at":"2026-07-05T10:05:13.928841+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.20359","citing_title":"Train, Retrieve, or Both? A Four-Arm Head-to-Head for Correct Statutory Citation on the Ontario Residential Tenancies Act","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2502.13957","citing_title":"Supervising the search process produces reliable and generalizable information-seeking agents","ref_index":88,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XOFMGYIBTDWFYSAXQESJJNFI6X","json":"https://pith.science/pith/XOFMGYIBTDWFYSAXQESJJNFI6X.json","graph_json":"https://pith.science/api/pith-number/XOFMGYIBTDWFYSAXQESJJNFI6X/graph.json","events_json":"https://pith.science/api/pith-number/XOFMGYIBTDWFYSAXQESJJNFI6X/events.json","paper":"https://pith.science/paper/XOFMGYIB"},"agent_actions":{"view_html":"https://pith.science/pith/XOFMGYIBTDWFYSAXQESJJNFI6X","download_json":"https://pith.science/pith/XOFMGYIBTDWFYSAXQESJJNFI6X.json","view_paper":"https://pith.science/paper/XOFMGYIB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.17952&json=true","fetch_graph":"https://pith.science/api/pith-number/XOFMGYIBTDWFYSAXQESJJNFI6X/graph.json","fetch_events":"https://pith.science/api/pith-number/XOFMGYIBTDWFYSAXQESJJNFI6X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XOFMGYIBTDWFYSAXQESJJNFI6X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XOFMGYIBTDWFYSAXQESJJNFI6X/action/storage_attestation","attest_author":"https://pith.science/pith/XOFMGYIBTDWFYSAXQESJJNFI6X/action/author_attestation","sign_citation":"https://pith.science/pith/XOFMGYIBTDWFYSAXQESJJNFI6X/action/citation_signature","submit_replication":"https://pith.science/pith/XOFMGYIBTDWFYSAXQESJJNFI6X/action/replication_record"}},"created_at":"2026-07-05T10:05:13.928841+00:00","updated_at":"2026-07-05T10:05:13.928841+00:00"}