{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:S6OVKD3YSJCOL5LOJFEQYREUDJ","short_pith_number":"pith:S6OVKD3Y","schema_version":"1.0","canonical_sha256":"979d550f789244e5f56e49490c44941a676b4f4b85d85f48706a89ddb34930e9","source":{"kind":"arxiv","id":"2305.01555","version":4},"attestation_state":"computed","paper":{"title":"How to Unleash the Power of Large Language Models for Few-shot Relation Extraction?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.DB","cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Ningyu Zhang, Xiaohan Wang, Xin Xu, Yuqi Zhu","submitted_at":"2023-05-02T15:55:41Z","abstract_excerpt":"Scaling language models have revolutionized widespread NLP tasks, yet little comprehensively explored few-shot relation extraction with large language models. In this paper, we investigate principal methodologies, in-context learning and data generation, for few-shot relation extraction via GPT-3.5 through exhaustive experiments. To enhance few-shot performance, we further propose task-related instructions and schema-constrained data generation. We observe that in-context learning can achieve performance on par with previous prompt learning approaches, and data generation with the large langua"},"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":"2305.01555","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-02T15:55:41Z","cross_cats_sorted":["cs.AI","cs.DB","cs.IR","cs.LG"],"title_canon_sha256":"e98456710bf454fba4fc11e619d4029d938d072643931a4f3e70356adc042b8c","abstract_canon_sha256":"f924195e8a922b3a52806f9560984cfe513436b53a582db72d29abdd04da2435"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:19:03.738409Z","signature_b64":"wrW+tFqSY5Phcht13kXuhvVd1c0i08bPUa9GDEs63Fwc4vlESGfSATNN22GpgNhQHGMm40fnkck7V+Q0saGjCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"979d550f789244e5f56e49490c44941a676b4f4b85d85f48706a89ddb34930e9","last_reissued_at":"2026-07-05T06:19:03.737906Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:19:03.737906Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"How to Unleash the Power of Large Language Models for Few-shot Relation Extraction?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.DB","cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Ningyu Zhang, Xiaohan Wang, Xin Xu, Yuqi Zhu","submitted_at":"2023-05-02T15:55:41Z","abstract_excerpt":"Scaling language models have revolutionized widespread NLP tasks, yet little comprehensively explored few-shot relation extraction with large language models. In this paper, we investigate principal methodologies, in-context learning and data generation, for few-shot relation extraction via GPT-3.5 through exhaustive experiments. To enhance few-shot performance, we further propose task-related instructions and schema-constrained data generation. We observe that in-context learning can achieve performance on par with previous prompt learning approaches, and data generation with the large langua"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.01555","kind":"arxiv","version":4},"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/2305.01555/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":"2305.01555","created_at":"2026-07-05T06:19:03.737967+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.01555v4","created_at":"2026-07-05T06:19:03.737967+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.01555","created_at":"2026-07-05T06:19:03.737967+00:00"},{"alias_kind":"pith_short_12","alias_value":"S6OVKD3YSJCO","created_at":"2026-07-05T06:19:03.737967+00:00"},{"alias_kind":"pith_short_16","alias_value":"S6OVKD3YSJCOL5LO","created_at":"2026-07-05T06:19:03.737967+00:00"},{"alias_kind":"pith_short_8","alias_value":"S6OVKD3Y","created_at":"2026-07-05T06:19:03.737967+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.03102","citing_title":"Small RL Controller, Large Language Model: RL-Guided Adaptive Sampling for Test-Time Scaling","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/S6OVKD3YSJCOL5LOJFEQYREUDJ","json":"https://pith.science/pith/S6OVKD3YSJCOL5LOJFEQYREUDJ.json","graph_json":"https://pith.science/api/pith-number/S6OVKD3YSJCOL5LOJFEQYREUDJ/graph.json","events_json":"https://pith.science/api/pith-number/S6OVKD3YSJCOL5LOJFEQYREUDJ/events.json","paper":"https://pith.science/paper/S6OVKD3Y"},"agent_actions":{"view_html":"https://pith.science/pith/S6OVKD3YSJCOL5LOJFEQYREUDJ","download_json":"https://pith.science/pith/S6OVKD3YSJCOL5LOJFEQYREUDJ.json","view_paper":"https://pith.science/paper/S6OVKD3Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.01555&json=true","fetch_graph":"https://pith.science/api/pith-number/S6OVKD3YSJCOL5LOJFEQYREUDJ/graph.json","fetch_events":"https://pith.science/api/pith-number/S6OVKD3YSJCOL5LOJFEQYREUDJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S6OVKD3YSJCOL5LOJFEQYREUDJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S6OVKD3YSJCOL5LOJFEQYREUDJ/action/storage_attestation","attest_author":"https://pith.science/pith/S6OVKD3YSJCOL5LOJFEQYREUDJ/action/author_attestation","sign_citation":"https://pith.science/pith/S6OVKD3YSJCOL5LOJFEQYREUDJ/action/citation_signature","submit_replication":"https://pith.science/pith/S6OVKD3YSJCOL5LOJFEQYREUDJ/action/replication_record"}},"created_at":"2026-07-05T06:19:03.737967+00:00","updated_at":"2026-07-05T06:19:03.737967+00:00"}