{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XNGQ2632RLVBGMXHWKD4RUBS3V","short_pith_number":"pith:XNGQ2632","schema_version":"1.0","canonical_sha256":"bb4d0d7b7a8aea1332e7b287c8d032dd4726b4e06050cbc2e3500ed2a7dc7e8c","source":{"kind":"arxiv","id":"2405.14431","version":1},"attestation_state":"computed","paper":{"title":"RaFe: Ranking Feedback Improves Query Rewriting for RAG","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Boli Chen, Fei Huang, Huajun Chen, Ningyu Zhang, Pengjun Xie, Peng Wang, Shengyu Mao, Xiao Li, Xinyu Wang, Yong Jiang","submitted_at":"2024-05-23T11:00:19Z","abstract_excerpt":"As Large Language Models (LLMs) and Retrieval Augmentation Generation (RAG) techniques have evolved, query rewriting has been widely incorporated into the RAG system for downstream tasks like open-domain QA. Many works have attempted to utilize small models with reinforcement learning rather than costly LLMs to improve query rewriting. However, current methods require annotations (e.g., labeled relevant documents or downstream answers) or predesigned rewards for feedback, which lack generalization, and fail to utilize signals tailored for query rewriting. In this paper, we propose ours, a fram"},"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":"2405.14431","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-23T11:00:19Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"ac4bf62f1184bdb55dedd4150c73cb67b75c9cde29fbeaf62fce0540d3212400","abstract_canon_sha256":"57dfd3dfd09c3e8b4ec8a222ea3ff45316bec13de1a2a9c9b1a5d86fbc4d9d07"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:22:14.537401Z","signature_b64":"LqYIpePVP2rDgteTyCETzqt9gin6VxaqouoHC8xExhYIkMWTTR8yuDHDFigfA8niJIW9W+uepkSTgqPCZDvaDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bb4d0d7b7a8aea1332e7b287c8d032dd4726b4e06050cbc2e3500ed2a7dc7e8c","last_reissued_at":"2026-07-05T08:22:14.536951Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:22:14.536951Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RaFe: Ranking Feedback Improves Query Rewriting for RAG","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Boli Chen, Fei Huang, Huajun Chen, Ningyu Zhang, Pengjun Xie, Peng Wang, Shengyu Mao, Xiao Li, Xinyu Wang, Yong Jiang","submitted_at":"2024-05-23T11:00:19Z","abstract_excerpt":"As Large Language Models (LLMs) and Retrieval Augmentation Generation (RAG) techniques have evolved, query rewriting has been widely incorporated into the RAG system for downstream tasks like open-domain QA. Many works have attempted to utilize small models with reinforcement learning rather than costly LLMs to improve query rewriting. However, current methods require annotations (e.g., labeled relevant documents or downstream answers) or predesigned rewards for feedback, which lack generalization, and fail to utilize signals tailored for query rewriting. In this paper, we propose ours, a fram"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.14431","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/2405.14431/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":"2405.14431","created_at":"2026-07-05T08:22:14.537013+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.14431v1","created_at":"2026-07-05T08:22:14.537013+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.14431","created_at":"2026-07-05T08:22:14.537013+00:00"},{"alias_kind":"pith_short_12","alias_value":"XNGQ2632RLVB","created_at":"2026-07-05T08:22:14.537013+00:00"},{"alias_kind":"pith_short_16","alias_value":"XNGQ2632RLVBGMXH","created_at":"2026-07-05T08:22:14.537013+00:00"},{"alias_kind":"pith_short_8","alias_value":"XNGQ2632","created_at":"2026-07-05T08:22:14.537013+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2505.14558","citing_title":"R2MED: A Benchmark for Reasoning-Driven Medical Retrieval","ref_index":9,"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":216,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XNGQ2632RLVBGMXHWKD4RUBS3V","json":"https://pith.science/pith/XNGQ2632RLVBGMXHWKD4RUBS3V.json","graph_json":"https://pith.science/api/pith-number/XNGQ2632RLVBGMXHWKD4RUBS3V/graph.json","events_json":"https://pith.science/api/pith-number/XNGQ2632RLVBGMXHWKD4RUBS3V/events.json","paper":"https://pith.science/paper/XNGQ2632"},"agent_actions":{"view_html":"https://pith.science/pith/XNGQ2632RLVBGMXHWKD4RUBS3V","download_json":"https://pith.science/pith/XNGQ2632RLVBGMXHWKD4RUBS3V.json","view_paper":"https://pith.science/paper/XNGQ2632","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.14431&json=true","fetch_graph":"https://pith.science/api/pith-number/XNGQ2632RLVBGMXHWKD4RUBS3V/graph.json","fetch_events":"https://pith.science/api/pith-number/XNGQ2632RLVBGMXHWKD4RUBS3V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XNGQ2632RLVBGMXHWKD4RUBS3V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XNGQ2632RLVBGMXHWKD4RUBS3V/action/storage_attestation","attest_author":"https://pith.science/pith/XNGQ2632RLVBGMXHWKD4RUBS3V/action/author_attestation","sign_citation":"https://pith.science/pith/XNGQ2632RLVBGMXHWKD4RUBS3V/action/citation_signature","submit_replication":"https://pith.science/pith/XNGQ2632RLVBGMXHWKD4RUBS3V/action/replication_record"}},"created_at":"2026-07-05T08:22:14.537013+00:00","updated_at":"2026-07-05T08:22:14.537013+00:00"}