ChatGPT给语言大模型带来的启示和多模态大模型新的发展思路  

The Inspiration Brought by ChatGPT to LLM and the New Development Ideas of Multi-modal Large Model

作　　者：赵朝阳 朱贵波 王金桥[1] Zhao Chaoyang;Zhu Guibo;Wang Jinqiao(Institute of Automation,Chinese Academy of Sciences,Beijing 100190,China)

机构地区：[1]中国科学院自动化研究所,北京100190

出　　处：《数据分析与知识发现》2023年第3期26-35,共10页Data Analysis and Knowledge Discovery

基　　金：国家自然科学基金项目(项目编号:61976210,62176254)的研究成果之一。

摘　　要：【目的】剖析ChatGPT的基础技术原理,探讨其对大语言模型发展产生的影响,以及对多模态大模型发展思路产生的影响。【方法】通过分析ChatGPT的发展过程和技术原理,探讨指令微调、数据采集与标注、基于人类反馈的强化学习等模型构建方法对大语言模型产生的影响。分析当前多模态大模型构建过程中遇到的关键科学问题,并借鉴ChatGPT的技术方案,探讨多模态大模型未来的发展发展思路。【结论】ChatGPT为预训练大模型向下游任务的发展提供了良好的参考技术路径,未来的多模态大模型构建以及下游任务实现过程中,可以充分利用高质量的指令微调等技术来显著提升多模态大模型的下游任务性能。[Objective]This paper analyzes the basic technical principles of ChatGPT,and discusses its influence on the development of large language model and the development of multi-modal pretrained model.[Methods]By analyzing the development process and technical principles of ChatGPT,this paper discusses the influence of model building methods such as instruct fine-tuning,data acquisition and annotation,and reinforcement learning based on human feedback on the large language model.At the same time,this paper analyzes several key scientific problems encountered in the construction of multi-modal model,and discusses the future development of multi-modal pretrained model by referring to ChatGPT’s technical scheme.[Conclusions]The success of ChatGPT provides a good reference technology path for the development of pretrained fundamental model to downstream tasks.In the future construction of multi-modal large model and the realization of downstream tasks,we can make full use of high-quality instruction fine-tuning and other technologies to significantly improve the performance of downstream tasks.

关 键 词：语言大模型 预训练大模型 多模态预训练模型 ChatGPT 

分 类 号：TP393[自动化与计算机技术—计算机应用技术] G250[自动化与计算机技术—计算机科学与技术]