{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:EOQJIZ2GR2UAMVSNLQNE4UFKCX","short_pith_number":"pith:EOQJIZ2G","schema_version":"1.0","canonical_sha256":"23a09467468ea806564d5c1a4e50aa15d9f65d9c3d5feab200d47c1e2a51109e","source":{"kind":"arxiv","id":"2305.14283","version":3},"attestation_state":"computed","paper":{"title":"Query Rewriting for Retrieval-Augmented Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hai Zhao, Nan Duan, Pengcheng He, Xinbei Ma, Yeyun Gong","submitted_at":"2023-05-23T17:27:50Z","abstract_excerpt":"Large Language Models (LLMs) play powerful, black-box readers in the retrieve-then-read pipeline, making remarkable progress in knowledge-intensive tasks. This work introduces a new framework, Rewrite-Retrieve-Read instead of the previous retrieve-then-read for the retrieval-augmented LLMs from the perspective of the query rewriting. Unlike prior studies focusing on adapting either the retriever or the reader, our approach pays attention to the adaptation of the search query itself, for there is inevitably a gap between the input text and the needed knowledge in retrieval. We first prompt an L"},"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":"2305.14283","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T17:27:50Z","cross_cats_sorted":[],"title_canon_sha256":"648c60421cbaea4839c030c8a2831997d8ac3c4f4880c91d3f8c7e922b905bd0","abstract_canon_sha256":"bd46fae9a2129c2567ca263ab0580e4433be8a3a08e11fe0d5f0f86a61fa22bd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:03:25.372535Z","signature_b64":"kESE3ssQY18ILS6wc9ubS8MEnQfft9cj7YQz0rmVt+zRem9J/949/h24894nkng5um5AapqywnqB5sVO+U7kBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"23a09467468ea806564d5c1a4e50aa15d9f65d9c3d5feab200d47c1e2a51109e","last_reissued_at":"2026-07-05T07:03:25.372059Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:03:25.372059Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Query Rewriting for Retrieval-Augmented Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hai Zhao, Nan Duan, Pengcheng He, Xinbei Ma, Yeyun Gong","submitted_at":"2023-05-23T17:27:50Z","abstract_excerpt":"Large Language Models (LLMs) play powerful, black-box readers in the retrieve-then-read pipeline, making remarkable progress in knowledge-intensive tasks. This work introduces a new framework, Rewrite-Retrieve-Read instead of the previous retrieve-then-read for the retrieval-augmented LLMs from the perspective of the query rewriting. Unlike prior studies focusing on adapting either the retriever or the reader, our approach pays attention to the adaptation of the search query itself, for there is inevitably a gap between the input text and the needed knowledge in retrieval. We first prompt an L"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.14283","kind":"arxiv","version":3},"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/2305.14283/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":"2305.14283","created_at":"2026-07-05T07:03:25.372121+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.14283v3","created_at":"2026-07-05T07:03:25.372121+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.14283","created_at":"2026-07-05T07:03:25.372121+00:00"},{"alias_kind":"pith_short_12","alias_value":"EOQJIZ2GR2UA","created_at":"2026-07-05T07:03:25.372121+00:00"},{"alias_kind":"pith_short_16","alias_value":"EOQJIZ2GR2UAMVSN","created_at":"2026-07-05T07:03:25.372121+00:00"},{"alias_kind":"pith_short_8","alias_value":"EOQJIZ2G","created_at":"2026-07-05T07:03:25.372121+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":20,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.13438","citing_title":"CQC-RAG: Robust Retrieval-Augmented Generation via Cross-Query Consistency","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27440","citing_title":"Paraphrase Brittleness in Production Retrieval-Augmented Commercial Recommendation: Reproducibility Below the Rerun-Stability Baseline","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30862","citing_title":"Sophrosyne: Agentic Exploration of Relational Data Systems Needs Moderation","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2312.10997","citing_title":"Retrieval-Augmented Generation for Large Language Models: A Survey","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2409.10102","citing_title":"Trustworthiness in Retrieval-Augmented Generation Systems: A Survey","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2411.08249","citing_title":"Retrieval Augmented Time Series Forecasting","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14057","citing_title":"Dual Hierarchical Dialogue Policy Learning for Legal Inquisitive Conversational Agents","ref_index":114,"is_internal_anchor":false},{"citing_arxiv_id":"2506.04565","citing_title":"From Standalone LLMs to Integrated Intelligence: A Survey of Compound Al Systems","ref_index":115,"is_internal_anchor":false},{"citing_arxiv_id":"2506.18027","citing_title":"PDF Retrieval Augmented Question Answering","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2504.21776","citing_title":"WebThinker: Empowering Large Reasoning Models with Deep Research Capability","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09579","citing_title":"Help Without Being Asked: A Deployed Proactive Agent System for On-Call Support with Continuous Self-Improvement","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14057","citing_title":"Dual Hierarchical Dialogue Policy Learning for Legal Inquisitive Conversational Agents","ref_index":114,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14503","citing_title":"Not All RAGs Are Created Equal: A Component-Wise Empirical Study for Software Engineering Tasks","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2501.05366","citing_title":"Search-o1: Agentic Search-Enhanced Large Reasoning Models","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2604.03675","citing_title":"OASES: Outcome-Aligned Search-Evaluation Co-Training for Agentic Search","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2311.05232","citing_title":"A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions","ref_index":209,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22280","citing_title":"Beyond Chain-of-Thought: Rewrite as a Universal Interface for Generative Multimodal Embeddings","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12735","citing_title":"AffectAgent: Collaborative Multi-Agent Reasoning for Retrieval-Augmented Multimodal Emotion Recognition","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07201","citing_title":"BRIDGE: Multimodal-to-Text Retrieval via Reinforcement-Learned Query Alignment","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14222","citing_title":"Adaptive Query Routing: A Tier-Based Framework for Hybrid Retrieval Across Financial, Legal, and Medical Documents","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EOQJIZ2GR2UAMVSNLQNE4UFKCX","json":"https://pith.science/pith/EOQJIZ2GR2UAMVSNLQNE4UFKCX.json","graph_json":"https://pith.science/api/pith-number/EOQJIZ2GR2UAMVSNLQNE4UFKCX/graph.json","events_json":"https://pith.science/api/pith-number/EOQJIZ2GR2UAMVSNLQNE4UFKCX/events.json","paper":"https://pith.science/paper/EOQJIZ2G"},"agent_actions":{"view_html":"https://pith.science/pith/EOQJIZ2GR2UAMVSNLQNE4UFKCX","download_json":"https://pith.science/pith/EOQJIZ2GR2UAMVSNLQNE4UFKCX.json","view_paper":"https://pith.science/paper/EOQJIZ2G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.14283&json=true","fetch_graph":"https://pith.science/api/pith-number/EOQJIZ2GR2UAMVSNLQNE4UFKCX/graph.json","fetch_events":"https://pith.science/api/pith-number/EOQJIZ2GR2UAMVSNLQNE4UFKCX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EOQJIZ2GR2UAMVSNLQNE4UFKCX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EOQJIZ2GR2UAMVSNLQNE4UFKCX/action/storage_attestation","attest_author":"https://pith.science/pith/EOQJIZ2GR2UAMVSNLQNE4UFKCX/action/author_attestation","sign_citation":"https://pith.science/pith/EOQJIZ2GR2UAMVSNLQNE4UFKCX/action/citation_signature","submit_replication":"https://pith.science/pith/EOQJIZ2GR2UAMVSNLQNE4UFKCX/action/replication_record"}},"created_at":"2026-07-05T07:03:25.372121+00:00","updated_at":"2026-07-05T07:03:25.372121+00:00"}