{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:BI7TU7IIWYFXWF3IG5KAL5VHM3","short_pith_number":"pith:BI7TU7II","schema_version":"1.0","canonical_sha256":"0a3f3a7d08b60b7b1768375405f6a766c1a720f9023f8574d527d64bf4c6f600","source":{"kind":"arxiv","id":"2209.10063","version":3},"attestation_state":"computed","paper":{"title":"Generate rather than Retrieve: Large Language Models are Strong Context Generators","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chenguang Zhu, Dan Iter, Meng Jiang, Michael Zeng, Mingxuan Ju, Shuohang Wang, Soumya Sanyal, Wenhao Yu, Yichong Xu","submitted_at":"2022-09-21T01:30:59Z","abstract_excerpt":"Knowledge-intensive tasks, such as open-domain question answering (QA), require access to a large amount of world or domain knowledge. A common approach for knowledge-intensive tasks is to employ a retrieve-then-read pipeline that first retrieves a handful of relevant contextual documents from an external corpus such as Wikipedia and then predicts an answer conditioned on the retrieved documents. In this paper, we present a novel perspective for solving knowledge-intensive tasks by replacing document retrievers with large language model generators. We call our method generate-then-read (GenRea"},"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":"2209.10063","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-09-21T01:30:59Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"dd73038cc271127ee49161fe53b91bb40a585dc1b81d88c3be22ac936b14fd13","abstract_canon_sha256":"6b8a039d1948b6824f40c579401dc1b05c1b2e08e2086b4778a6f9cbd989121e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:35:46.481275Z","signature_b64":"yDJw4RtuD8qvfWGQk1LVUFLM0aR5rbahnVtYER97c4WoDeiU6RBNSAR2HiAHeGCJ2mrWZNXXPJpysh4AjsOVCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0a3f3a7d08b60b7b1768375405f6a766c1a720f9023f8574d527d64bf4c6f600","last_reissued_at":"2026-07-05T05:35:46.480784Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:35:46.480784Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generate rather than Retrieve: Large Language Models are Strong Context Generators","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chenguang Zhu, Dan Iter, Meng Jiang, Michael Zeng, Mingxuan Ju, Shuohang Wang, Soumya Sanyal, Wenhao Yu, Yichong Xu","submitted_at":"2022-09-21T01:30:59Z","abstract_excerpt":"Knowledge-intensive tasks, such as open-domain question answering (QA), require access to a large amount of world or domain knowledge. A common approach for knowledge-intensive tasks is to employ a retrieve-then-read pipeline that first retrieves a handful of relevant contextual documents from an external corpus such as Wikipedia and then predicts an answer conditioned on the retrieved documents. In this paper, we present a novel perspective for solving knowledge-intensive tasks by replacing document retrievers with large language model generators. We call our method generate-then-read (GenRea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.10063","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/2209.10063/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":"2209.10063","created_at":"2026-07-05T05:35:46.480836+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.10063v3","created_at":"2026-07-05T05:35:46.480836+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.10063","created_at":"2026-07-05T05:35:46.480836+00:00"},{"alias_kind":"pith_short_12","alias_value":"BI7TU7IIWYFX","created_at":"2026-07-05T05:35:46.480836+00:00"},{"alias_kind":"pith_short_16","alias_value":"BI7TU7IIWYFXWF3I","created_at":"2026-07-05T05:35:46.480836+00:00"},{"alias_kind":"pith_short_8","alias_value":"BI7TU7II","created_at":"2026-07-05T05:35:46.480836+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2312.10997","citing_title":"Retrieval-Augmented Generation for Large Language Models: A Survey","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2505.04588","citing_title":"ZeroSearch: Incentivize the Search Capability of LLMs without Searching","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2511.02805","citing_title":"MemSearcher: Training LLMs to Reason, Search and Manage Memory via End-to-End Reinforcement Learning","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2505.04588","citing_title":"ZeroSearch: Incentivize the Search Capability of LLMs without Searching","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2402.19473","citing_title":"Retrieval-Augmented Generation for AI-Generated Content: A Survey","ref_index":163,"is_internal_anchor":false},{"citing_arxiv_id":"2401.18059","citing_title":"RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval","ref_index":61,"is_internal_anchor":false},{"citing_arxiv_id":"2310.11511","citing_title":"Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection","ref_index":74,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08519","citing_title":"Cram Less to Fit More: Training Data Pruning Improves Memorization of Facts","ref_index":95,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BI7TU7IIWYFXWF3IG5KAL5VHM3","json":"https://pith.science/pith/BI7TU7IIWYFXWF3IG5KAL5VHM3.json","graph_json":"https://pith.science/api/pith-number/BI7TU7IIWYFXWF3IG5KAL5VHM3/graph.json","events_json":"https://pith.science/api/pith-number/BI7TU7IIWYFXWF3IG5KAL5VHM3/events.json","paper":"https://pith.science/paper/BI7TU7II"},"agent_actions":{"view_html":"https://pith.science/pith/BI7TU7IIWYFXWF3IG5KAL5VHM3","download_json":"https://pith.science/pith/BI7TU7IIWYFXWF3IG5KAL5VHM3.json","view_paper":"https://pith.science/paper/BI7TU7II","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.10063&json=true","fetch_graph":"https://pith.science/api/pith-number/BI7TU7IIWYFXWF3IG5KAL5VHM3/graph.json","fetch_events":"https://pith.science/api/pith-number/BI7TU7IIWYFXWF3IG5KAL5VHM3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BI7TU7IIWYFXWF3IG5KAL5VHM3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BI7TU7IIWYFXWF3IG5KAL5VHM3/action/storage_attestation","attest_author":"https://pith.science/pith/BI7TU7IIWYFXWF3IG5KAL5VHM3/action/author_attestation","sign_citation":"https://pith.science/pith/BI7TU7IIWYFXWF3IG5KAL5VHM3/action/citation_signature","submit_replication":"https://pith.science/pith/BI7TU7IIWYFXWF3IG5KAL5VHM3/action/replication_record"}},"created_at":"2026-07-05T05:35:46.480836+00:00","updated_at":"2026-07-05T05:35:46.480836+00:00"}