Open Information Extraction (OIE) task aims at extracting structured facts from unstructured text, typically in the form of (subject, relation, object) triples. Despite the potential of large language models (LLMs) like ChatGPT as a general task solver, they lag behind state-of-the-art (supervised) methods in OIE tasks due to two key issues. First, LLMs struggle to distinguish irrelevant context from relevant relations and generate structured output due to the restrictions on fine-tuning the model. Second, LLMs generates responses autoregressively based on probability, which makes the predicted relations lack confidence. In this paper, we assess the capabilities of LLMs in improving the OIE task. Particularly, we propose various in-context learning strategies to enhance LLM's instruction-following ability and a demonstration uncertainty quantification module to enhance the confidence of the generated relations. Our experiments on three OIE benchmark datasets show that our approach holds its own against established supervised methods, both quantitatively and qualitatively.
ICL-D3IE: In-Context Learning with Diverse Demonstrations Updating for Document Information Extraction
University of Electronic Science and Technology of China(电子科技大学);Singapore Management University(新加坡管理大学);Beijing Forestry University(北京林业大学);Beijing Rongda Technology Co., Ltd.(北京融达科技有限公司)
LLM-based MOFs Synthesis Condition Extraction using Few-Shot Demonstrations
School of Computer Science, Beihang University(北京航空航天大学计算机学院);School of Materials Science & Engineering, University of Science and Technology Beijing(北京科技大学材料科学与工程学院);Westlake University(西湖大学)
Improving Input-label Mapping with Demonstration Replay for In-context Learning
Meituan(美团);Wangxuan Institute of Computer Technology, Peking University(北京大学王选计算机研究所);Meta AI;National Key Laboratory of General Artificial Intelligence(通用人工智能全国重点实验室);Beijing Institute for General Artificial Intelligence(北京通用人工智能研究院);Gaoling School of Artificial Intelligence, Renmin University of China(中国人民大学高瓴人工智能学院)
Delta-KNN: Improving Demonstration Selection in In-Context Learning for Alzheimer's Disease Detection
Department of Computer Science(计算机科学系);Vancouver Stroke Program and Division of Neurology, Faculty of Medicine(温哥华卒中计划和神经病学系,医学院);The University of British Columbia(不列颠哥伦比亚大学)
LLM-OREF: An Open Relation Extraction Framework Based on Large Language Models
School of Informatics, Xiamen University(厦门大学信息学院);LLM Team, Shopee Pte. Ltd.(Shopee Pte. Ltd. 机器学习团队);National Institute for Data Science in Health and Medicine, Xiamen University(厦门大学医学数据科学国家研究院)
PANDAS: Improving Many-shot Jailbreaking via Positive Affirmation, Negative Demonstration, and Adaptive Sampling
University of Toronto, Vector Institute(多伦多大学,向量研究所);University of Oxford(牛津大学);Polytechnique Montréal, Mila - Quebec AI Institute, University of Toronto(蒙特利尔理工学院,魁北克人工智能研究所,多伦多大学)
Recall, Retrieve and Reason: Towards Better In-Context Relation Extraction
School of Computer Science and Engineering, Southeast University(东南大学计算机科学与工程学院);Beijing Institute of Computer Technology and Application(北京计算机技术及应用研究所);Interdisciplinary Applications (Southeast University), Ministry of Education(教育部东南大学交叉应用中心)
TEGEE: Task dEfinition Guided Expert Ensembling for Generalizable and Few-shot Learning
HKUST(香港科技大学);University of Manchester(曼彻斯特大学);Institute of Automation, CAS(中国科学院自动化研究所);University of Chinese Academy of Sciences(中国科学院大学);M-A-P;Beijing University of Posts and Telecommunications(北京邮电大学);Ohio State University(俄亥俄州立大学);University of Waterloo(滑铁卢大学);Peking University(北京大学);BAAI(北京智源人工智能研究院)
ZS4IE: A toolkit for Zero-Shot Information Extraction with simple Verbalizations
HiTZ Basque Center for Language Technologies(HiTZ巴斯克语言技术中心);Raytheon BBN Technologies(雷神BBN技术公司);University of the Basque Country (UPV/EHU)(巴斯克大学(UPV/EHU))
Layout-Aware Information Extraction for Document-Grounded Dialogue: Dataset, Method and Demonstration
Institute of Information Engineering, Chinese Academy of Sciences(中国科学院信息工程研究所);School of Cyber Security, University of Chinese Academy of Sciences(中国科学院大学网络空间安全学院);DAMO Academy, Alibaba Group(阿里巴巴集团达摩院)
Improving Neural Protein-Protein Interaction Extraction with Knowledge Selection
School of Computer Science and Technology, Dalian University of Technology(大连理工大学计算机科学与技术学院);School of Mathematical Sciences, Dalian University of Technology(大连理工大学数学科学学院)
从已发表的科学文献中提取蛋白质-蛋白质相互作用(PPI)为精准医学工作提供了额外的支持。同时,知识库(KBs)包含了大量的蛋白质实体及其关系的结构化信息,这些信息可以编码在实体和关系嵌入中,以帮助PPI提取。然而,必须有选择地使用蛋白质-蛋白质对的先验知识,以便它适用于不同的背景。本文提出了一种知识选择模型(KSM)融合选择的先验知识和上下文信息的PPI提取。首先,两个Transformers根据每个蛋白质嵌入分别编码蛋白质对的上下文序列。然后,将两个输出馈送到相互关注以捕获针对蛋白质对的重要上下文特征。然后,利用上下文特征通过知识选择器提取关系嵌入。最后,所选择的关系嵌入和上下文特征连接PPI提取。在BioCreative VI PPI数据集上的实验表明,KSM通过添加知识选择实现了新的最先进的性能(38.08%F1分数)。
Improving unsupervised neural aspect extraction for online discussions using out-of-domain classification
Samsung-PDMI Joint AI Center, Steklov Mathematical Institute(三星-圣彼得堡数学研究所联合人工智能中心,斯捷克洛夫数学研究所);National Research University Higher School of Economics(国立研究型大学高等经济学院);Kazan Federal University(喀山联邦大学);Moscow Institute of Physics and Technology(莫斯科物理技术学院)
InteractiveIE: Towards Assessing the Strength of Human-AI Collaboration in Improving the Performance of Information Extraction
University of Maryland(马里兰大学);Amazon(亚马逊公司);Adobe Research(奥多比研究院);University of Maryland, Baltimore County(马里兰大学巴尔的摩县分校);John Hopkins University(约翰霍普金斯大学);University of Maryland School of Law(马里兰大学法学院)