{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:GVO3KIUIQEUBEXD5TDLPZVDK5Z","short_pith_number":"pith:GVO3KIUI","schema_version":"1.0","canonical_sha256":"355db522888128125c7d98d6fcd46aee5af75ac2e8885f636f16011e43e02896","source":{"kind":"arxiv","id":"2307.07164","version":2},"attestation_state":"computed","paper":{"title":"Learning to Retrieve In-Context Examples for Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Furu Wei, Liang Wang, Nan Yang","submitted_at":"2023-07-14T05:23:08Z","abstract_excerpt":"Large language models (LLMs) have demonstrated their ability to learn in-context, allowing them to perform various tasks based on a few input-output examples. However, the effectiveness of in-context learning is heavily reliant on the quality of the selected examples. In this paper, we propose a novel framework to iteratively train dense retrievers that can identify high-quality in-context examples for LLMs. Our framework initially trains a reward model based on LLM feedback to evaluate the quality of candidate examples, followed by knowledge distillation to train a bi-encoder based dense retr"},"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":"2307.07164","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-14T05:23:08Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"3b719976dec7f05eda24baf1b6eecaebe20a179503d2176b7652bd06134353d9","abstract_canon_sha256":"8590ebdc69c12848b19a4a61b2e8a45c9e908802c84dc1b229e8f8c003065eb9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:37:50.438473Z","signature_b64":"S1YlEjrS8Cq/Vukm/pJw0NnjggonalGh7XC1XXQB/GuzKjaWNdbC9LBZkH0IufrI+Xkd3AR5o/3dkEpDSqO4Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"355db522888128125c7d98d6fcd46aee5af75ac2e8885f636f16011e43e02896","last_reissued_at":"2026-07-05T07:37:50.438012Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:37:50.438012Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning to Retrieve In-Context Examples for Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Furu Wei, Liang Wang, Nan Yang","submitted_at":"2023-07-14T05:23:08Z","abstract_excerpt":"Large language models (LLMs) have demonstrated their ability to learn in-context, allowing them to perform various tasks based on a few input-output examples. However, the effectiveness of in-context learning is heavily reliant on the quality of the selected examples. In this paper, we propose a novel framework to iteratively train dense retrievers that can identify high-quality in-context examples for LLMs. Our framework initially trains a reward model based on LLM feedback to evaluate the quality of candidate examples, followed by knowledge distillation to train a bi-encoder based dense retr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.07164","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/2307.07164/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":"2307.07164","created_at":"2026-07-05T07:37:50.438074+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.07164v2","created_at":"2026-07-05T07:37:50.438074+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.07164","created_at":"2026-07-05T07:37:50.438074+00:00"},{"alias_kind":"pith_short_12","alias_value":"GVO3KIUIQEUB","created_at":"2026-07-05T07:37:50.438074+00:00"},{"alias_kind":"pith_short_16","alias_value":"GVO3KIUIQEUBEXD5","created_at":"2026-07-05T07:37:50.438074+00:00"},{"alias_kind":"pith_short_8","alias_value":"GVO3KIUI","created_at":"2026-07-05T07:37:50.438074+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.12744","citing_title":"GRIP: Feedback-Guided Prompt Retrieval for Large Multimodal Models","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2407.04573","citing_title":"Vector Retrieval with Similarity and Diversity: How Hard Is It?","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2312.10997","citing_title":"Retrieval-Augmented Generation for Large Language Models: A Survey","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2410.20791","citing_title":"From Cool Demos to Production-Ready FMware: Core Challenges and a Technology Roadmap","ref_index":105,"is_internal_anchor":false},{"citing_arxiv_id":"2307.06435","citing_title":"A Comprehensive Overview of Large Language Models","ref_index":206,"is_internal_anchor":false},{"citing_arxiv_id":"2506.16453","citing_title":"Understanding the Challenges and Opportunities of Generative AI Apps: An Empirical Study","ref_index":74,"is_internal_anchor":false},{"citing_arxiv_id":"2402.19473","citing_title":"Retrieval-Augmented Generation for AI-Generated Content: A Survey","ref_index":156,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05396","citing_title":"Reason Analogically via Cross-domain Prior Knowledge: An Empirical Study of Cross-domain Knowledge Transfer for In-Context Learning","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05383","citing_title":"Towards Effective In-context Cross-domain Knowledge Transfer via Domain-invariant-neurons-based Retrieval","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GVO3KIUIQEUBEXD5TDLPZVDK5Z","json":"https://pith.science/pith/GVO3KIUIQEUBEXD5TDLPZVDK5Z.json","graph_json":"https://pith.science/api/pith-number/GVO3KIUIQEUBEXD5TDLPZVDK5Z/graph.json","events_json":"https://pith.science/api/pith-number/GVO3KIUIQEUBEXD5TDLPZVDK5Z/events.json","paper":"https://pith.science/paper/GVO3KIUI"},"agent_actions":{"view_html":"https://pith.science/pith/GVO3KIUIQEUBEXD5TDLPZVDK5Z","download_json":"https://pith.science/pith/GVO3KIUIQEUBEXD5TDLPZVDK5Z.json","view_paper":"https://pith.science/paper/GVO3KIUI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.07164&json=true","fetch_graph":"https://pith.science/api/pith-number/GVO3KIUIQEUBEXD5TDLPZVDK5Z/graph.json","fetch_events":"https://pith.science/api/pith-number/GVO3KIUIQEUBEXD5TDLPZVDK5Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GVO3KIUIQEUBEXD5TDLPZVDK5Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GVO3KIUIQEUBEXD5TDLPZVDK5Z/action/storage_attestation","attest_author":"https://pith.science/pith/GVO3KIUIQEUBEXD5TDLPZVDK5Z/action/author_attestation","sign_citation":"https://pith.science/pith/GVO3KIUIQEUBEXD5TDLPZVDK5Z/action/citation_signature","submit_replication":"https://pith.science/pith/GVO3KIUIQEUBEXD5TDLPZVDK5Z/action/replication_record"}},"created_at":"2026-07-05T07:37:50.438074+00:00","updated_at":"2026-07-05T07:37:50.438074+00:00"}