{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:F7C55MXG7UY3YFZL4B6JFS6BOL","short_pith_number":"pith:F7C55MXG","schema_version":"1.0","canonical_sha256":"2fc5deb2e6fd31bc172be07c92cbc172ce0008566c2b0a0c0c450956ecc2a305","source":{"kind":"arxiv","id":"2303.08559","version":2},"attestation_state":"computed","paper":{"title":"Large Language Model Is Not a Good Few-shot Information Extractor, but a Good Reranker for Hard Samples!","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Aixin Sun, Yixin Cao, YongChing Hong, Yubo Ma","submitted_at":"2023-03-15T12:20:13Z","abstract_excerpt":"Large Language Models (LLMs) have made remarkable strides in various tasks. Whether LLMs are competitive few-shot solvers for information extraction (IE) tasks, however, remains an open problem. In this work, we aim to provide a thorough answer to this question. Through extensive experiments on nine datasets across four IE tasks, we demonstrate that current advanced LLMs consistently exhibit inferior performance, higher latency, and increased budget requirements compared to fine-tuned SLMs under most settings. Therefore, we conclude that LLMs are not effective few-shot information extractors i"},"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":"2303.08559","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-03-15T12:20:13Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"326f5b1b0bf487027deba71482d9a96b6d79eac24a44a732ae7889eaaf823fa1","abstract_canon_sha256":"e129e1cae79b9361117779e6194fbc748a0b2edfc3848ad99df6ec72b09eb7d9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:07:09.139216Z","signature_b64":"07d1lE1a/4bPfKmuqF9PIwCLjHhpjzfjc8DqDZjny4UFM1xxnxtQdGcfXk4svAGdAMbGyoVhCr70VYnPKv7ECw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2fc5deb2e6fd31bc172be07c92cbc172ce0008566c2b0a0c0c450956ecc2a305","last_reissued_at":"2026-07-05T08:07:09.138729Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:07:09.138729Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Large Language Model Is Not a Good Few-shot Information Extractor, but a Good Reranker for Hard Samples!","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Aixin Sun, Yixin Cao, YongChing Hong, Yubo Ma","submitted_at":"2023-03-15T12:20:13Z","abstract_excerpt":"Large Language Models (LLMs) have made remarkable strides in various tasks. Whether LLMs are competitive few-shot solvers for information extraction (IE) tasks, however, remains an open problem. In this work, we aim to provide a thorough answer to this question. Through extensive experiments on nine datasets across four IE tasks, we demonstrate that current advanced LLMs consistently exhibit inferior performance, higher latency, and increased budget requirements compared to fine-tuned SLMs under most settings. Therefore, we conclude that LLMs are not effective few-shot information extractors i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.08559","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/2303.08559/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":"2303.08559","created_at":"2026-07-05T08:07:09.138788+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.08559v2","created_at":"2026-07-05T08:07:09.138788+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.08559","created_at":"2026-07-05T08:07:09.138788+00:00"},{"alias_kind":"pith_short_12","alias_value":"F7C55MXG7UY3","created_at":"2026-07-05T08:07:09.138788+00:00"},{"alias_kind":"pith_short_16","alias_value":"F7C55MXG7UY3YFZL","created_at":"2026-07-05T08:07:09.138788+00:00"},{"alias_kind":"pith_short_8","alias_value":"F7C55MXG","created_at":"2026-07-05T08:07:09.138788+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.02743","citing_title":"Geometric Decoherence Time in Lindbladian Dynamics","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2312.10997","citing_title":"Retrieval-Augmented Generation for Large Language Models: A Survey","ref_index":103,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21525","citing_title":"Job Skill Extraction via LLM-Centric Multi-Module Framework","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/F7C55MXG7UY3YFZL4B6JFS6BOL","json":"https://pith.science/pith/F7C55MXG7UY3YFZL4B6JFS6BOL.json","graph_json":"https://pith.science/api/pith-number/F7C55MXG7UY3YFZL4B6JFS6BOL/graph.json","events_json":"https://pith.science/api/pith-number/F7C55MXG7UY3YFZL4B6JFS6BOL/events.json","paper":"https://pith.science/paper/F7C55MXG"},"agent_actions":{"view_html":"https://pith.science/pith/F7C55MXG7UY3YFZL4B6JFS6BOL","download_json":"https://pith.science/pith/F7C55MXG7UY3YFZL4B6JFS6BOL.json","view_paper":"https://pith.science/paper/F7C55MXG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.08559&json=true","fetch_graph":"https://pith.science/api/pith-number/F7C55MXG7UY3YFZL4B6JFS6BOL/graph.json","fetch_events":"https://pith.science/api/pith-number/F7C55MXG7UY3YFZL4B6JFS6BOL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F7C55MXG7UY3YFZL4B6JFS6BOL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F7C55MXG7UY3YFZL4B6JFS6BOL/action/storage_attestation","attest_author":"https://pith.science/pith/F7C55MXG7UY3YFZL4B6JFS6BOL/action/author_attestation","sign_citation":"https://pith.science/pith/F7C55MXG7UY3YFZL4B6JFS6BOL/action/citation_signature","submit_replication":"https://pith.science/pith/F7C55MXG7UY3YFZL4B6JFS6BOL/action/replication_record"}},"created_at":"2026-07-05T08:07:09.138788+00:00","updated_at":"2026-07-05T08:07:09.138788+00:00"}