{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:QCUI23Z2KD3ZNXWTYN7VXWURAD","short_pith_number":"pith:QCUI23Z2","schema_version":"1.0","canonical_sha256":"80a88d6f3a50f796ded3c37f5bda9100daaba417c4de942160e88ff3f771ffd5","source":{"kind":"arxiv","id":"2304.08085","version":1},"attestation_state":"computed","paper":{"title":"InstructUIE: Multi-task Instruction Tuning for Unified Information Extraction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Can Zu, Chunsai Du, Han Xia, Jihua Kang, Jingsheng Yang, Junjie Ye, Qi Zhang, Rui Zheng, Siyuan Li, Tao Gui, Tianze Chen, Weikang Zhou, Xiao Wang, Yuansen Zhang","submitted_at":"2023-04-17T09:00:50Z","abstract_excerpt":"Large language models have unlocked strong multi-task capabilities from reading instructive prompts. However, recent studies have shown that existing large models still have difficulty with information extraction tasks. For example, gpt-3.5-turbo achieved an F1 score of 18.22 on the Ontonotes dataset, which is significantly lower than the state-of-the-art performance. In this paper, we propose InstructUIE, a unified information extraction framework based on instruction tuning, which can uniformly model various information extraction tasks and capture the inter-task dependency. To validate the "},"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":"2304.08085","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-04-17T09:00:50Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e4b2d0b910c5eb2a1092a1dd5c7133dfb702ce89ce9520290db65a700d24ac6f","abstract_canon_sha256":"fe46a9d374b372fdb6bfd50fff62cd672a926d82bddabe234e48facc7ad31261"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:01:39.154187Z","signature_b64":"ZbwzFgbTszC9M6zxNrKPA3OM5c8cWiUPZSGxoGo2ZOgs36an0b0boXGlwMKHfXEDBa4Q9aCexg4i1Fnl/N1LDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"80a88d6f3a50f796ded3c37f5bda9100daaba417c4de942160e88ff3f771ffd5","last_reissued_at":"2026-07-05T06:01:39.153715Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:01:39.153715Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"InstructUIE: Multi-task Instruction Tuning for Unified Information Extraction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Can Zu, Chunsai Du, Han Xia, Jihua Kang, Jingsheng Yang, Junjie Ye, Qi Zhang, Rui Zheng, Siyuan Li, Tao Gui, Tianze Chen, Weikang Zhou, Xiao Wang, Yuansen Zhang","submitted_at":"2023-04-17T09:00:50Z","abstract_excerpt":"Large language models have unlocked strong multi-task capabilities from reading instructive prompts. However, recent studies have shown that existing large models still have difficulty with information extraction tasks. For example, gpt-3.5-turbo achieved an F1 score of 18.22 on the Ontonotes dataset, which is significantly lower than the state-of-the-art performance. In this paper, we propose InstructUIE, a unified information extraction framework based on instruction tuning, which can uniformly model various information extraction tasks and capture the inter-task dependency. To validate the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.08085","kind":"arxiv","version":1},"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/2304.08085/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":"2304.08085","created_at":"2026-07-05T06:01:39.153772+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.08085v1","created_at":"2026-07-05T06:01:39.153772+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.08085","created_at":"2026-07-05T06:01:39.153772+00:00"},{"alias_kind":"pith_short_12","alias_value":"QCUI23Z2KD3Z","created_at":"2026-07-05T06:01:39.153772+00:00"},{"alias_kind":"pith_short_16","alias_value":"QCUI23Z2KD3ZNXWT","created_at":"2026-07-05T06:01:39.153772+00:00"},{"alias_kind":"pith_short_8","alias_value":"QCUI23Z2","created_at":"2026-07-05T06:01:39.153772+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":12,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.00008","citing_title":"SchemaRAG: Dynamic Large Schema Reduction for LLM-driven Structured Information Extraction","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28070","citing_title":"JD Oxygen AI Item Center (Oxygen AIIC) V1: An Industrial-Scale LLM/VLM-Centric Solution for Item Understanding, Management, and Applications","ref_index":82,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18113","citing_title":"iPOE: Interpretable Prompt Optimization via Explanations","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28070","citing_title":"JD Oxygen AI Item Center (Oxygen AIIC) V1: An Industrial-Scale LLM/VLM-Centric Solution for Item Understanding, Management, and Applications","ref_index":82,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29407","citing_title":"LC-ICL: Label-Guided Contrastive In-Context Learning for Robust Information Extraction","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2406.14075","citing_title":"EXCEEDS: Extracting Complex Events via Nugget-based Grid Modeling in Scientific Domain","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2604.01674","citing_title":"Can Heterogeneous Language Models Be Fused?","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27479","citing_title":"Gender Bias in YouTube Exposure: Allocative and Structural Inequalities in Political Information Environments","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03706","citing_title":"SAM-NER: Semantic Archetype Mediation for Zero-Shot Named Entity Recognition","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21525","citing_title":"Job Skill Extraction via LLM-Centric Multi-Module Framework","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10212","citing_title":"Relational Probing: LM-to-Graph Adaptation for Financial Prediction","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03103","citing_title":"MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QCUI23Z2KD3ZNXWTYN7VXWURAD","json":"https://pith.science/pith/QCUI23Z2KD3ZNXWTYN7VXWURAD.json","graph_json":"https://pith.science/api/pith-number/QCUI23Z2KD3ZNXWTYN7VXWURAD/graph.json","events_json":"https://pith.science/api/pith-number/QCUI23Z2KD3ZNXWTYN7VXWURAD/events.json","paper":"https://pith.science/paper/QCUI23Z2"},"agent_actions":{"view_html":"https://pith.science/pith/QCUI23Z2KD3ZNXWTYN7VXWURAD","download_json":"https://pith.science/pith/QCUI23Z2KD3ZNXWTYN7VXWURAD.json","view_paper":"https://pith.science/paper/QCUI23Z2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.08085&json=true","fetch_graph":"https://pith.science/api/pith-number/QCUI23Z2KD3ZNXWTYN7VXWURAD/graph.json","fetch_events":"https://pith.science/api/pith-number/QCUI23Z2KD3ZNXWTYN7VXWURAD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QCUI23Z2KD3ZNXWTYN7VXWURAD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QCUI23Z2KD3ZNXWTYN7VXWURAD/action/storage_attestation","attest_author":"https://pith.science/pith/QCUI23Z2KD3ZNXWTYN7VXWURAD/action/author_attestation","sign_citation":"https://pith.science/pith/QCUI23Z2KD3ZNXWTYN7VXWURAD/action/citation_signature","submit_replication":"https://pith.science/pith/QCUI23Z2KD3ZNXWTYN7VXWURAD/action/replication_record"}},"created_at":"2026-07-05T06:01:39.153772+00:00","updated_at":"2026-07-05T06:01:39.153772+00:00"}