{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:QHRDASOY3L24PI4P2KGSAKZX4S","short_pith_number":"pith:QHRDASOY","schema_version":"1.0","canonical_sha256":"81e23049d8daf5c7a38fd28d202b37e483dd6947158eb5c316b2d48277fe5c1f","source":{"kind":"arxiv","id":"2304.14233","version":2},"attestation_state":"computed","paper":{"title":"Large Language Models are Strong Zero-Shot Retriever","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Chongyang Tao, Daxin Jiang, Guodong Long, Tao Shen, Tianyi Zhou, Xiubo Geng","submitted_at":"2023-04-27T14:45:55Z","abstract_excerpt":"In this work, we propose a simple method that applies a large language model (LLM) to large-scale retrieval in zero-shot scenarios. Our method, the Language language model as Retriever (LameR), is built upon no other neural models but an LLM, while breaking brute-force combinations of retrievers with LLMs and lifting the performance of zero-shot retrieval to be very competitive on benchmark datasets. Essentially, we propose to augment a query with its potential answers by prompting LLMs with a composition of the query and the query's in-domain candidates. The candidates, regardless of correct "},"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":"2304.14233","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-04-27T14:45:55Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"2c4e5f23e4fa98743d7f6b58d740c22197ec666162a8825ac050835423049b4e","abstract_canon_sha256":"51d2f1084a1b01756b723071be423914a9a768c0acba9bc89284753430e9ffb4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:36:54.512298Z","signature_b64":"KPVkDr9wSsxLasPQ9CBlB0/o0cbzu0uXn/g80QlYf5Dba2hvaPOuhST3qFpwePpZfwHthupbieDTnsCgGfujDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"81e23049d8daf5c7a38fd28d202b37e483dd6947158eb5c316b2d48277fe5c1f","last_reissued_at":"2026-07-05T06:36:54.511811Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:36:54.511811Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Large Language Models are Strong Zero-Shot Retriever","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Chongyang Tao, Daxin Jiang, Guodong Long, Tao Shen, Tianyi Zhou, Xiubo Geng","submitted_at":"2023-04-27T14:45:55Z","abstract_excerpt":"In this work, we propose a simple method that applies a large language model (LLM) to large-scale retrieval in zero-shot scenarios. Our method, the Language language model as Retriever (LameR), is built upon no other neural models but an LLM, while breaking brute-force combinations of retrievers with LLMs and lifting the performance of zero-shot retrieval to be very competitive on benchmark datasets. Essentially, we propose to augment a query with its potential answers by prompting LLMs with a composition of the query and the query's in-domain candidates. The candidates, regardless of correct "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.14233","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/2304.14233/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":"2304.14233","created_at":"2026-07-05T06:36:54.511868+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.14233v2","created_at":"2026-07-05T06:36:54.511868+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.14233","created_at":"2026-07-05T06:36:54.511868+00:00"},{"alias_kind":"pith_short_12","alias_value":"QHRDASOY3L24","created_at":"2026-07-05T06:36:54.511868+00:00"},{"alias_kind":"pith_short_16","alias_value":"QHRDASOY3L24PI4P","created_at":"2026-07-05T06:36:54.511868+00:00"},{"alias_kind":"pith_short_8","alias_value":"QHRDASOY","created_at":"2026-07-05T06:36:54.511868+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25237","citing_title":"Extreme Meta-Classification for Large-Scale Zero-Shot Retrieval","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2509.07794","citing_title":"Query Expansion in the Age of Pre-trained and Large Language Models: A Comprehensive Survey","ref_index":99,"is_internal_anchor":false},{"citing_arxiv_id":"2402.13116","citing_title":"A Survey on Knowledge Distillation of Large Language Models","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QHRDASOY3L24PI4P2KGSAKZX4S","json":"https://pith.science/pith/QHRDASOY3L24PI4P2KGSAKZX4S.json","graph_json":"https://pith.science/api/pith-number/QHRDASOY3L24PI4P2KGSAKZX4S/graph.json","events_json":"https://pith.science/api/pith-number/QHRDASOY3L24PI4P2KGSAKZX4S/events.json","paper":"https://pith.science/paper/QHRDASOY"},"agent_actions":{"view_html":"https://pith.science/pith/QHRDASOY3L24PI4P2KGSAKZX4S","download_json":"https://pith.science/pith/QHRDASOY3L24PI4P2KGSAKZX4S.json","view_paper":"https://pith.science/paper/QHRDASOY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.14233&json=true","fetch_graph":"https://pith.science/api/pith-number/QHRDASOY3L24PI4P2KGSAKZX4S/graph.json","fetch_events":"https://pith.science/api/pith-number/QHRDASOY3L24PI4P2KGSAKZX4S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QHRDASOY3L24PI4P2KGSAKZX4S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QHRDASOY3L24PI4P2KGSAKZX4S/action/storage_attestation","attest_author":"https://pith.science/pith/QHRDASOY3L24PI4P2KGSAKZX4S/action/author_attestation","sign_citation":"https://pith.science/pith/QHRDASOY3L24PI4P2KGSAKZX4S/action/citation_signature","submit_replication":"https://pith.science/pith/QHRDASOY3L24PI4P2KGSAKZX4S/action/replication_record"}},"created_at":"2026-07-05T06:36:54.511868+00:00","updated_at":"2026-07-05T06:36:54.511868+00:00"}