本工作使用最先进的语言模型 GPT-3，为知识库开发提供一种新颖的信息抽取方法。所提出的方法旨在解决从非结构化文本中获取相关实体和关系以抽取结构化信息所面临的困难。我们在来自不同领域的大规模文本语料库上进行实验，以评估所提出技术的性能。评估指标包括信息抽取任务中常用的精确率、召回率和 F1 分数。结果表明，GPT-3 可用于高效且准确地从文本中抽取相关且正确的信息，从而提高知识库创建的精确率和生产率。我们还将所提出方法的性能与现有最先进的信息抽取技术进行比较。结果显示，通过在上下文学习中仅使用少量样本，我们提出的策略取得了具有竞争力的结果，并显著节省了数据标注和工程成本。此外，我们使用所提出的方法检索生物医学信息，证明了其在真实场景中的实用性。总体而言，我们提出的方法为克服从非结构化文本中获取结构化数据以创建知识库所涉及的困难提供了一种可行途径。它可以显著提高信息抽取的精确率和效率，而这对于聊天机器人、推荐引擎和问答系统等许多应用都是必要的。
英文摘要：
This work uses the state-of-the-art language model GPT-3 to offer a novel method of information extraction for knowledge base development. The suggested method attempts to solve the difficulties associated with obtaining relevant entities and relationships from unstructured text in order to extract structured information. We conduct experiments on a huge corpus of text from diverse fields to assess the performance of our suggested technique. The evaluation measures, which are frequently employed in information extraction tasks, include precision, recall, and F1-score. The findings demonstrate that GPT-3 can be used to efficiently and accurately extract pertinent and correct information from text, hence increasing the precision and productivity of knowledge base creation. We also assess how well our suggested approach performs in comparison to the most advanced information extraction techniques already in use. The findings show that by utilizing only a small number of instances in in-context learning, our suggested strategy yields competitive outcomes with notable savings in terms of data annotation and engineering expense. Additionally, we use our proposed method to retrieve Biomedical information, demonstrating its practicality in a real-world setting. All things considered, our suggested method offers a viable way to overcome the difficulties involved in obtaining structured data from unstructured text in order to create knowledge bases. It can greatly increase the precision and effectiveness of information extraction, which is necessary for many applications including chatbots, recommendation engines, and question-answering systems.
GCRE-GPT: A Generative Model for Comparative Relation Extraction
Beijing Academy of Artificial Intelligence（北京人工智能研究院）；Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；University of Chinese Academy of Sciences（中国科学院大学）；School of Computer Science and Engineering, Nanyang Technological University（南洋理工大学计算机科学与工程学院）
Automated Information Extraction from Thyroid Operation Narrative: A Comparative Study of GPT-4 and Fine-tuned KoELECTRA
Seoul National University（首尔大学）；Ewha Womans University Medical Center（梨花女子大学医疗院）；Seoul National University Hospital and College of Medicine（首尔大学医院暨医学院）
Use GPT-J Prompt Generation with RoBERTa for NER Models on Diagnosis Extraction of Periodontal Diagnosis from Electronic Dental Records
McWilliams School of Biomedical Informatics, University of Texas Health Science Center at Houston（德克萨斯大学休斯顿健康科学中心麦克威廉姆斯生物医学信息学学院）；University of Texas Health Science Center at Houston School of Dentistry（德克萨斯大学休斯顿健康科学中心牙科学院）；Temple University Kornberg School of Dentistry（天普大学科恩伯格牙科学院）
本研究利用 GPT-J 提示生成结合 RoBERTa 模型，从电子牙科记录中提取牙周诊断，发现种子质量比数量更重要，且 RoBERTa 训练后 F1 达 0.92-0.97。
Can large language models replace humans in the systematic review process? Evaluating GPT-4's efficacy in screening and extracting data from peer-reviewed and grey literature in multiple languages
Trinity Centre for Global Health（三一全球健康中心）；School of Psychology（心理学院）；Trinity College Dublin（都柏林圣三一学院）；University of York（约克大学）
RATE: An LLM-Powered Retrieval Augmented Generation Technology-Extraction Pipeline
Dept. of Management, Science and Technology（管理、科学与技术系）；Amirkabir University of Technology（阿姆尔卡比尔科技大学）；Dept. of Electrical Engineering（电气工程系）；Sharif University of Technology（沙里夫科技大学）
Comparison of pipeline, sequence-to-sequence, and GPT models for end-to-end relation extraction: experiments with the rare disease use-case
Computer Science Department, University of Kentucky, USA（肯塔基大学计算机科学系）；Division of Biomedical Informatics, Dept. of Internal Medicine, University of Kentucky, USA（肯塔基大学生物医学信息学部）
Leveraging Fine-Tuned Large Language Models for Interpretable Pancreatic Cystic Lesion Feature Extraction and Risk Categorization
New York University（纽约大学）；Columbia University Irving Medical Center（哥伦比亚大学欧文医学中心）；NYU Grossman School of Medicine（纽约大学格罗斯曼医学院）；University of California San Diego（加州大学圣地亚哥分校）
Relation Extraction Using Large Language Models: A Case Study on Acupuncture Point Locations
The University of Texas Health Science Center at Houston（德克萨斯大学休斯顿健康科学中心）；Yale University（耶鲁大学）；Mayo Clinic（妙佑医疗国际）；China Academy of Chinese Medical Sciences（中国中医科学院）；The University of Texas MD Anderson Cancer Center（德克萨斯大学MD安德森癌症中心）
本文以 WHO 标准的 361 个穴位、3,174 个定位关系为语料，比较 GPT 与 LSTM、BioBERT 的关系抽取性能，发现微调 GPT-3.5 表现最佳，微平均 F1 达 0.92。
Fine-tuning Pre-Trained Transformer Language Models to Distantly Supervised Relation Extraction
German Research Center for Artificial Intelligence (DFKI)（德国人工智能研究中心）
距离监督关系抽取被广泛用于从文本中抽取关系事实，但受到噪声标签的影响。当前的关系抽取方法试图通过多实例学习来减轻噪声，并通过提供支持语言和上下文信息来更有效地指导关系分类。在实现最先进的结果的同时，我们观察到这些模型偏向于以高精度识别有限的关系集，而忽略了长尾中的关系。为了解决这一差距，我们利用了一个预训练的语言模型，OpenAI生成预训练的Transformer（GPT）[Radford et al.，2018年]。GPT和类似的模型已被证明可以捕获语义和句法特征，以及大量的“常识”知识，我们假设这些知识是识别更多样化关系的重要特征。通过将GPT扩展到远程监督设置，并在NYT10数据集上对其进行微调，我们表明它可以预测更大的一组具有高置信度的不同关系类型。对我们模型的手动和自动评估表明，它在NYT10数据集上实现了最先进的AUC得分0.422，并且在较高的召回水平下表现得特别好。
Improving Entity Recognition Using Ensembles of Deep Learning and Fine-tuned Large Language Models: A Case Study on Adverse Event Extraction from Multiple Sources
McWilliams School of Biomedical Informatics, The University of Texas Health Science Center at Houston（德克萨斯大学休斯顿健康科学中心麦克威廉姆斯生物医学信息学院）；Pratt School of Engineering, Duke University（杜克大学普拉特工程学院）；Mayo Clinic（梅奥诊所）；School of Medicine, Yale University（耶鲁大学医学院）
From UNDRR Reports to Event Records: Schema-Constrained LLM Extraction of Georeferenced Disasters
ETH Zürich（苏黎世联邦理工学院）；University of Maryland（马里兰大学）；MPI（马克斯·普朗克研究所）；University of Toronto（多伦多大学）；United Nations Office for Disaster Risk Reduction（联合国减少灾害风险办公室）
Institute for AI Industry Research (AIR), Tsinghua University（清华大学人工智能产业研究院（AIR））；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；University of Notre Dame（圣母大学）；Microsoft Research（微软研究院）；Department of Automation, Tsinghua University（清华大学自动化系）
SPL: A Socratic Playground for Learning Powered by Large Language Model
Institute for Intelligent Systems, University of Memphis（孟菲斯大学智能系统研究所）；University of Memphis（孟菲斯大学）；School of Computer Science, Carnegie Mellon University（卡内基梅隆大学计算机科学学院）；School of Psychology, Shaanxi Normal University（陕西师范大学心理学院）；School of Psychology, Central China Normal University（华中师范大学心理学院）；Department of Applied Social Sciences, Hong Kong Polytechnic University（香港理工大学应用社会科学系）
