{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:WTJFCLMZOYIA4UBE2ILOSR2TIS","short_pith_number":"pith:WTJFCLMZ","schema_version":"1.0","canonical_sha256":"b4d2512d9976100e5024d216e9475344aedd9a01e13b4af748e0bd19902cbe9d","source":{"kind":"arxiv","id":"2312.17617","version":3},"attestation_state":"computed","paper":{"title":"Large Language Models for Generative Information Extraction: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chao Zhang, Derong Xu, Enhong Chen, Tong Xu, Wei Chen, Wenjun Peng, Xiangyu Zhao, Xian Wu, Yang Wang, Yefeng Zheng","submitted_at":"2023-12-29T14:25:22Z","abstract_excerpt":"Information extraction (IE) aims to extract structural knowledge from plain natural language texts. Recently, generative Large Language Models (LLMs) have demonstrated remarkable capabilities in text understanding and generation. As a result, numerous works have been proposed to integrate LLMs for IE tasks based on a generative paradigm. To conduct a comprehensive systematic review and exploration of LLM efforts for IE tasks, in this study, we survey the most recent advancements in this field. We first present an extensive overview by categorizing these works in terms of various IE subtasks an"},"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":"2312.17617","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-12-29T14:25:22Z","cross_cats_sorted":[],"title_canon_sha256":"e237a36d6fd3e0c70226096b7d38aa1175babfb379ba6fc7fb5fb30be36853ab","abstract_canon_sha256":"3a899039f1423a7760358338305e4a09f5a93d02d21ac4497ed6f0fea102ef94"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:28:47.014828Z","signature_b64":"ZtxoWCZDccRSyFV3cIDnXwoSDkO+AE0Wltejzj3pkZXLWJ3mZ7LAiRDltlHk9dOVw27R3oLNH8Ve0ovb4xx9DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b4d2512d9976100e5024d216e9475344aedd9a01e13b4af748e0bd19902cbe9d","last_reissued_at":"2026-07-05T09:28:47.014331Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:28:47.014331Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Large Language Models for Generative Information Extraction: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chao Zhang, Derong Xu, Enhong Chen, Tong Xu, Wei Chen, Wenjun Peng, Xiangyu Zhao, Xian Wu, Yang Wang, Yefeng Zheng","submitted_at":"2023-12-29T14:25:22Z","abstract_excerpt":"Information extraction (IE) aims to extract structural knowledge from plain natural language texts. Recently, generative Large Language Models (LLMs) have demonstrated remarkable capabilities in text understanding and generation. As a result, numerous works have been proposed to integrate LLMs for IE tasks based on a generative paradigm. To conduct a comprehensive systematic review and exploration of LLM efforts for IE tasks, in this study, we survey the most recent advancements in this field. We first present an extensive overview by categorizing these works in terms of various IE subtasks an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.17617","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/2312.17617/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":"2312.17617","created_at":"2026-07-05T09:28:47.014383+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.17617v3","created_at":"2026-07-05T09:28:47.014383+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.17617","created_at":"2026-07-05T09:28:47.014383+00:00"},{"alias_kind":"pith_short_12","alias_value":"WTJFCLMZOYIA","created_at":"2026-07-05T09:28:47.014383+00:00"},{"alias_kind":"pith_short_16","alias_value":"WTJFCLMZOYIA4UBE","created_at":"2026-07-05T09:28:47.014383+00:00"},{"alias_kind":"pith_short_8","alias_value":"WTJFCLMZ","created_at":"2026-07-05T09:28:47.014383+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.29407","citing_title":"LC-ICL: Label-Guided Contrastive In-Context Learning for Robust Information Extraction","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2508.19932","citing_title":"CASE: An Agentic AI Framework for Enhancing Scam Intelligence in Digital Payments","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2404.13501","citing_title":"A Survey on the Memory Mechanism of Large Language Model based Agents","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27906","citing_title":"From Unstructured Recall to Schema-Grounded Memory: Reliable AI Memory via Iterative, Schema-Aware Extraction","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25906","citing_title":"Make Any Collection Navigable: Methods for Constructing and Evaluating Hypergraph of Text","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14930","citing_title":"IE as Cache: Information Extraction Enhanced Agentic Reasoning","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WTJFCLMZOYIA4UBE2ILOSR2TIS","json":"https://pith.science/pith/WTJFCLMZOYIA4UBE2ILOSR2TIS.json","graph_json":"https://pith.science/api/pith-number/WTJFCLMZOYIA4UBE2ILOSR2TIS/graph.json","events_json":"https://pith.science/api/pith-number/WTJFCLMZOYIA4UBE2ILOSR2TIS/events.json","paper":"https://pith.science/paper/WTJFCLMZ"},"agent_actions":{"view_html":"https://pith.science/pith/WTJFCLMZOYIA4UBE2ILOSR2TIS","download_json":"https://pith.science/pith/WTJFCLMZOYIA4UBE2ILOSR2TIS.json","view_paper":"https://pith.science/paper/WTJFCLMZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.17617&json=true","fetch_graph":"https://pith.science/api/pith-number/WTJFCLMZOYIA4UBE2ILOSR2TIS/graph.json","fetch_events":"https://pith.science/api/pith-number/WTJFCLMZOYIA4UBE2ILOSR2TIS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WTJFCLMZOYIA4UBE2ILOSR2TIS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WTJFCLMZOYIA4UBE2ILOSR2TIS/action/storage_attestation","attest_author":"https://pith.science/pith/WTJFCLMZOYIA4UBE2ILOSR2TIS/action/author_attestation","sign_citation":"https://pith.science/pith/WTJFCLMZOYIA4UBE2ILOSR2TIS/action/citation_signature","submit_replication":"https://pith.science/pith/WTJFCLMZOYIA4UBE2ILOSR2TIS/action/replication_record"}},"created_at":"2026-07-05T09:28:47.014383+00:00","updated_at":"2026-07-05T09:28:47.014383+00:00"}