Large language models(LLMS)have shown excellent text generation capabilities, capable of generating fluent human-like responses for many downstream tasks. However, applying large language models to real-world critical tasks remains challenging due to their susceptibility to hallucinations and inability to directly use external knowledge. To cope with the above challenges, this paper proposes PatternGPT, a pattern-driven text generation framework for Large Language Models. Firstly, the framework utilizes the extraction capability of Large Language Models to generate rich and diversified structured and formalized patterns, which facilitates the introduction of external knowledge to do the computation, and then draws on the idea of federated learning to use multiple agents to achieve the sharing in order to obtain more diversified patterns, and finally uses judgment criteria and optimization algorithm to search for high-quality patterns to guide the generation of models. Finally, external knowledge such as judgment criteria and optimization algorithms are used to search for high-quality patterns, and the searched patterns are used to guide model generation. This framework has the advantages of generating diversified patterns, protecting data privacy, combining external knowledge, and improving the quality of generation, which provides an effective method to optimize the text generation capability of large language models, and make it better applied to the field of intelligent dialogue and content generation.
RepreGuard: Detecting LLM-Generated Text by Revealing Hidden Representation Patterns
NLP(自然语言处理);CT Lab, Department of Computer and Information Science, University of Macau(计算机与信息科学系,澳门大学);Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences(深圳先进技术研究院,中国科学院);Provable Responsible AI and Data Analytics Lab, KAUST(可证明责任AI与数据分析实验室,卡尔斯兰大学);Hong Kong Baptist University(香港 Baptist 大学)
Extracting Abstraction Dimensions by Identifying Syntax Pattern from Texts
Key Laboratory of Intelligent Information Processing(智能信息处理重点实验室);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);King’s College London(伦敦国王学院);Publicis Sapient;School of Computing and Information Technology(计算与信息科技学院);Great Bay University(大柏大学);Great Bay Institute for Advanced Study(大柏先进研究院)
Quantifying patterns of punctuation in modern Chinese prose
Faculty of Computer Science and Telecommunications, Cracow University of Technology(克拉科夫理工大学计算机科学与电信学院);Institute of Nuclear Physics, Polish Academy of Sciences(波兰科学院核物理研究所);School of Modern Languages, Georgia Institute of Technology(佐治亚理工学院现代语言学院)
PAMPO: using pattern matching and pos-tagging for effective Named Entities recognition in Portuguese
INESC TEC;FCUP(波尔图大学理学院);ICMC-USP(圣保罗大学圣卡洛斯数学与计算机科学研究所);University of São Paulo(圣保罗大学);FEP(波尔图大学经济学院)
本文论述了实体提取任务(命名实体识别)的文本挖掘过程,旨在揭示非平凡的语义结构,如实体或社区之间的关系和相互作用。本文提出了一种简单有效的命名实体抽取算法。该方法采用灵活的模式匹配、词性标注和基于词典的规则,称为PAMPO(Pattern Matching and PO s tagingbased algorithm for NER)。它被开发用于处理用葡萄牙语编写的文本,但它也可能适用于其他语言。我们比较我们的方法与目前的替代品,支持命名实体识别(NER)的内容写在葡萄牙语。这些是炼金术师泽曼塔和伦勃朗在葡萄牙语写的几个文本上的实体提取方法的疗效评价表明,$recall$和$F_1$措施有相当大的改善。
No Pattern, No Recognition: a Survey about Reproducibility and Distortion Issues of Text Clustering and Topic Modeling
Institute of Mathematics and Computer Science(数学与计算机科学研究所);University of São Paulo(圣保罗大学);São Carlos School of Engineering(圣卡洛斯工程学院);Institute of Informatics(信息学研究所);Federal University of Goiás(戈亚斯联邦大学)