{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/instructuie-multi-task-instruction-tuning-for","title":"InstructUIE: Multi-task Instruction Tuning for Unified Information Extraction","arxiv_id":"2304.08085","date":"2023-04-17","proceeding":null,"authors":["Xiao Wang","Weikang Zhou","Can Zu","Han Xia","Tianze Chen","Yuansen Zhang","Rui Zheng","Junjie Ye","Qi Zhang","Tao Gui","Jihua Kang","Jingsheng Yang","Siyuan Li","Chunsai Du"],"abstract":"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 proposed method, we introduce IE INSTRUCTIONS, a benchmark of 32 diverse information extraction datasets in a unified text-to-text format with expert-written instructions. Experimental results demonstrate that our method achieves comparable performance to Bert in supervised settings and significantly outperforms the state-of-the-art and gpt3.5 in zero-shot settings.","url_abs":"https://arxiv.org/abs/2304.08085v1","url_pdf":"https://arxiv.org/pdf/2304.08085v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"instructuie-multi-task-instruction-tuning-for","repo_url":"https://github.com/beyonderxx/instructuie","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"zero-shot-named-entity-recognition-ner","task_name":"Zero-shot Named Entity Recognition (NER)"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bert","method_name":"BERT"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-linear-decay","method_name":"Linear Warmup With Linear Decay"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"weight-decay","method_name":"Weight Decay"},{"method_slug":"wordpiece","method_name":"WordPiece"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/zero-shot-named-entity-recognition-ner-on-1","task":"Zero-shot Named Entity Recognition (NER)","dataset":"CrossNER","model":"InstructUIE","rank_in_archive_order":3,"of":4,"metrics":{"AI":"49.0","Literature":"47.2","Music":"53.2","Politics":"48.2","Science":"49.3"},"uses_additional_data":true}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2304.08085","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}