Generative Large Language Models Explained

被引：0

作者：

Yan, Xueming ^{[1
]}

Xiao, Yan ^{[2
]}

Jin, Yaochu ^{[3
]}

机构：

[1] Guangdong Univ Foreign Studies, Guangzhou, Peoples R China

[2] Shanghai Maritime Univ, Shanghai, Peoples R China

[3] Westlake Univ, Hangzhou, Peoples R China

来源：

IEEE COMPUTATIONAL INTELLIGENCE MAGAZINE | 2024年 / 19卷 / 04期

基金：

中国国家自然科学基金;

关键词：

Training data; Adaptation models; Large language models; Reinforcement learning; Chatbots; Prompt engineering; Natural language processing; Explainable AI;

D O I：

10.1109/MCI.2024.3431454

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Large Language Models (LLMs) such as OpenAI's ChatGPT have achieved surprisingly huge progresses in the field of Natural Language Processing (NLP). This paper aims to present an immersive introduction to LLMs from the perspective of generative models. The main components of the training process of LLMs are explained, and an example of LLMs for AI-generated contents is given. This short paper is a summary of the interactive full paper online available at IEEE Xplore, in which detailed examples interactively demonstrate the training and working mechanisms of LLMs.

引用

页码：45 / 46

页数：2