{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RPYWGQWHVAEQO77KTH2SPIC43M","short_pith_number":"pith:RPYWGQWH","schema_version":"1.0","canonical_sha256":"8bf16342c7a809077fea99f527a05cdb161e8f588d6910c0d581620586636007","source":{"kind":"arxiv","id":"2411.03957","version":1},"attestation_state":"computed","paper":{"title":"Fine-Grained Guidance for Retrievers: Leveraging LLMs' Feedback in Retrieval-Augmented Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Fan Wu, Fei Wu, Jingyuan Chen, Shengyu Zhang, Xueyu Hu, Yuhang Liu","submitted_at":"2024-11-06T14:42:39Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) has proven to be an effective method for mitigating hallucination issues inherent in large language models (LLMs). Previous approaches typically train retrievers based on semantic similarity, lacking optimization for RAG. More recent works have proposed aligning retrievers with the preference signals of LLMs. However, these preference signals are often difficult for dense retrievers, which typically have weaker language capabilities, to understand and learn effectively. Drawing inspiration from pedagogical theories like Guided Discovery Learning, we propose"},"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":"2411.03957","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-11-06T14:42:39Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5ff867f0d9053f032b9abfe60d7c78580082ed3315e4612f508e30aaaf518e06","abstract_canon_sha256":"d5a99c34b2b8020f24fbfec71cde81eba82437068546f547e4c9ac2463b9845f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:31:58.611991Z","signature_b64":"1Y3gOWgQUyMFPV+cwiyi2E7aBaHAM9OKRsftGrl+63r90+MIyU1ulopMP2y8MVEGQ/FDS3u4u9n3SPauGCo3CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8bf16342c7a809077fea99f527a05cdb161e8f588d6910c0d581620586636007","last_reissued_at":"2026-07-05T09:31:58.611637Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:31:58.611637Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fine-Grained Guidance for Retrievers: Leveraging LLMs' Feedback in Retrieval-Augmented Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Fan Wu, Fei Wu, Jingyuan Chen, Shengyu Zhang, Xueyu Hu, Yuhang Liu","submitted_at":"2024-11-06T14:42:39Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) has proven to be an effective method for mitigating hallucination issues inherent in large language models (LLMs). Previous approaches typically train retrievers based on semantic similarity, lacking optimization for RAG. More recent works have proposed aligning retrievers with the preference signals of LLMs. However, these preference signals are often difficult for dense retrievers, which typically have weaker language capabilities, to understand and learn effectively. Drawing inspiration from pedagogical theories like Guided Discovery Learning, we propose"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.03957","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/2411.03957/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":"2411.03957","created_at":"2026-07-05T09:31:58.611693+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.03957v1","created_at":"2026-07-05T09:31:58.611693+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.03957","created_at":"2026-07-05T09:31:58.611693+00:00"},{"alias_kind":"pith_short_12","alias_value":"RPYWGQWHVAEQ","created_at":"2026-07-05T09:31:58.611693+00:00"},{"alias_kind":"pith_short_16","alias_value":"RPYWGQWHVAEQO77K","created_at":"2026-07-05T09:31:58.611693+00:00"},{"alias_kind":"pith_short_8","alias_value":"RPYWGQWH","created_at":"2026-07-05T09:31:58.611693+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RPYWGQWHVAEQO77KTH2SPIC43M","json":"https://pith.science/pith/RPYWGQWHVAEQO77KTH2SPIC43M.json","graph_json":"https://pith.science/api/pith-number/RPYWGQWHVAEQO77KTH2SPIC43M/graph.json","events_json":"https://pith.science/api/pith-number/RPYWGQWHVAEQO77KTH2SPIC43M/events.json","paper":"https://pith.science/paper/RPYWGQWH"},"agent_actions":{"view_html":"https://pith.science/pith/RPYWGQWHVAEQO77KTH2SPIC43M","download_json":"https://pith.science/pith/RPYWGQWHVAEQO77KTH2SPIC43M.json","view_paper":"https://pith.science/paper/RPYWGQWH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.03957&json=true","fetch_graph":"https://pith.science/api/pith-number/RPYWGQWHVAEQO77KTH2SPIC43M/graph.json","fetch_events":"https://pith.science/api/pith-number/RPYWGQWHVAEQO77KTH2SPIC43M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RPYWGQWHVAEQO77KTH2SPIC43M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RPYWGQWHVAEQO77KTH2SPIC43M/action/storage_attestation","attest_author":"https://pith.science/pith/RPYWGQWHVAEQO77KTH2SPIC43M/action/author_attestation","sign_citation":"https://pith.science/pith/RPYWGQWHVAEQO77KTH2SPIC43M/action/citation_signature","submit_replication":"https://pith.science/pith/RPYWGQWHVAEQO77KTH2SPIC43M/action/replication_record"}},"created_at":"2026-07-05T09:31:58.611693+00:00","updated_at":"2026-07-05T09:31:58.611693+00:00"}