{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:M3RHN3XYEEQFHKUZUJB2EESIQF","short_pith_number":"pith:M3RHN3XY","schema_version":"1.0","canonical_sha256":"66e276eef8212053aa99a243a21248814f9802551ea449ee8076d38acac6bc19","source":{"kind":"arxiv","id":"2401.06954","version":2},"attestation_state":"computed","paper":{"title":"Bridging the Preference Gap between Retrievers and LLMs","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Cheng Li, Michael Bendersky, Mingyang Zhang, Qiaozhu Mei, Weize Kong, Zixuan Ke","submitted_at":"2024-01-13T02:20:17Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated superior results across a wide range of tasks, and Retrieval-augmented Generation (RAG) is an effective way to enhance the performance by locating relevant information and placing it into the context window of the LLM. However, the relationship between retrievers and LLMs in a RAG is still under-investigated. Most existing work treats the retriever and the LLM as independent components and leaves a gap between retrieving human-\"friendly\" information and assembling a LLM-\"friendly\" context. In this work, we examine a novel bridge mechanism. We vali"},"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":"2401.06954","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-13T02:20:17Z","cross_cats_sorted":[],"title_canon_sha256":"abb56c75310788a1a3b1d3675017ea2437a6081c976dad4172b3d64632354c85","abstract_canon_sha256":"dab7acc4300d7bcba6bd4bc7caf357147fb1cf1a16f9a5482f236e3372365794"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:47:28.083496Z","signature_b64":"XW6JaRu+Gfc2Cc/nCzjmBUv0Nq5zC14ze48oL2Clx8Vf2P5ZKV9k6+qGzWY3opmaf1V2wt2DNO/iUnS1T1KMCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"66e276eef8212053aa99a243a21248814f9802551ea449ee8076d38acac6bc19","last_reissued_at":"2026-07-05T07:47:28.082883Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:47:28.082883Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bridging the Preference Gap between Retrievers and LLMs","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Cheng Li, Michael Bendersky, Mingyang Zhang, Qiaozhu Mei, Weize Kong, Zixuan Ke","submitted_at":"2024-01-13T02:20:17Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated superior results across a wide range of tasks, and Retrieval-augmented Generation (RAG) is an effective way to enhance the performance by locating relevant information and placing it into the context window of the LLM. However, the relationship between retrievers and LLMs in a RAG is still under-investigated. Most existing work treats the retriever and the LLM as independent components and leaves a gap between retrieving human-\"friendly\" information and assembling a LLM-\"friendly\" context. In this work, we examine a novel bridge mechanism. We vali"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.06954","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/2401.06954/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":"2401.06954","created_at":"2026-07-05T07:47:28.082950+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.06954v2","created_at":"2026-07-05T07:47:28.082950+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.06954","created_at":"2026-07-05T07:47:28.082950+00:00"},{"alias_kind":"pith_short_12","alias_value":"M3RHN3XYEEQF","created_at":"2026-07-05T07:47:28.082950+00:00"},{"alias_kind":"pith_short_16","alias_value":"M3RHN3XYEEQFHKUZ","created_at":"2026-07-05T07:47:28.082950+00:00"},{"alias_kind":"pith_short_8","alias_value":"M3RHN3XY","created_at":"2026-07-05T07:47:28.082950+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2312.10997","citing_title":"Retrieval-Augmented Generation for Large Language Models: A Survey","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2604.03675","citing_title":"OASES: Outcome-Aligned Search-Evaluation Co-Training for Agentic Search","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12735","citing_title":"AffectAgent: Collaborative Multi-Agent Reasoning for Retrieval-Augmented Multimodal Emotion Recognition","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/M3RHN3XYEEQFHKUZUJB2EESIQF","json":"https://pith.science/pith/M3RHN3XYEEQFHKUZUJB2EESIQF.json","graph_json":"https://pith.science/api/pith-number/M3RHN3XYEEQFHKUZUJB2EESIQF/graph.json","events_json":"https://pith.science/api/pith-number/M3RHN3XYEEQFHKUZUJB2EESIQF/events.json","paper":"https://pith.science/paper/M3RHN3XY"},"agent_actions":{"view_html":"https://pith.science/pith/M3RHN3XYEEQFHKUZUJB2EESIQF","download_json":"https://pith.science/pith/M3RHN3XYEEQFHKUZUJB2EESIQF.json","view_paper":"https://pith.science/paper/M3RHN3XY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.06954&json=true","fetch_graph":"https://pith.science/api/pith-number/M3RHN3XYEEQFHKUZUJB2EESIQF/graph.json","fetch_events":"https://pith.science/api/pith-number/M3RHN3XYEEQFHKUZUJB2EESIQF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M3RHN3XYEEQFHKUZUJB2EESIQF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M3RHN3XYEEQFHKUZUJB2EESIQF/action/storage_attestation","attest_author":"https://pith.science/pith/M3RHN3XYEEQFHKUZUJB2EESIQF/action/author_attestation","sign_citation":"https://pith.science/pith/M3RHN3XYEEQFHKUZUJB2EESIQF/action/citation_signature","submit_replication":"https://pith.science/pith/M3RHN3XYEEQFHKUZUJB2EESIQF/action/replication_record"}},"created_at":"2026-07-05T07:47:28.082950+00:00","updated_at":"2026-07-05T07:47:28.082950+00:00"}