Overview Research on the Use of Large Language Models (LLMs) in the Field of Software Engineering

EasyChair Preprint 14916

Abstract

Large Language Models (LLMs) are learning models with great depth, pre-trained on large amounts of data. This article aims to provide an overview of the use of major language models in the field of software engineering from January 2017 to December 2023. This article provides a survey of the area. The emerging field of Language Models for Software Engineering It also sets out extensive research formulations for the application of Language Models to deal with technical problems faced by software engineers. The outstanding characteristic of Language Model helps to bring novelties and creativity to the violation applications of Operational Software Engineering including coding, design, requirements, repair, regenerative structure, improve performance, documentation, and analytics. However, these emerging properties also pose significant technical challenges; We need techniques that can reliably eliminate imprecise solutions, such as hallucinations. Our survey helps me find roles that then leverage declarative Software Engineering development and development based on reliable and efficient language models.

Keyphrases: AI, PRISMA, Software Engineering, large language models, transformer

@booklet{EasyChair:14916,
  author    = {Việt Nguyễn Văn and Khánh Nguyễn Hữu and Duyên Nguyễn Thị and Huế Lương Thị Minh and Vịnh Nguyễn Thế and Công Nguyễn Hữu},
  title     = {Overview Research on the Use of Large Language Models (LLMs) in the Field of Software Engineering},
  howpublished = {EasyChair Preprint 14916},
  year      = {EasyChair, 2024}}