Towards an understanding of large language models in software engineering tasks
Abstract Large Language Models (LLMs) have drawn widespread attention and research
due to their astounding performance in text generation and reasoning tasks. Derivative …
due to their astounding performance in text generation and reasoning tasks. Derivative …
Generative Artificial Intelligence for Software Engineering--A Research Agenda
Generative Artificial Intelligence (GenAI) tools have become increasingly prevalent in
software development, offering assistance to various managerial and technical project …
software development, offering assistance to various managerial and technical project …
Large language models for software engineering: Survey and open problems
This paper provides a survey of the emerging area of Large Language Models (LLMs) for
Software Engineering (SE). It also sets out open research challenges for the application of …
Software Engineering (SE). It also sets out open research challenges for the application of …
LLM is Like a Box of Chocolates: the Non-determinism of ChatGPT in Code Generation
There has been a recent explosion of research on Large Language Models (LLMs) for
software engineering tasks, in particular code generation. However, results from LLMs can …
software engineering tasks, in particular code generation. However, results from LLMs can …
[HTML][HTML] Employing large language models in survey research
This article discusses the promising potential of employing large language models (LLMs)
for survey research, including generating responses to survey items. LLMs can address …
for survey research, including generating responses to survey items. LLMs can address …
An empirical study of the non-determinism of chatgpt in code generation
There has been a recent explosion of research on Large Language Models (LLMs) for
software engineering tasks, in particular code generation. However, results from LLMs can …
software engineering tasks, in particular code generation. However, results from LLMs can …
Automatic code summarization via chatgpt: How far are we?
To support software developers in understanding and maintaining programs, various
automatic code summarization techniques have been proposed to generate a concise …
automatic code summarization techniques have been proposed to generate a concise …
How to refactor this code? An exploratory study on developer-ChatGPT refactoring conversations
Large Language Models (LLMs), like ChatGPT, have gained widespread popularity and
usage in various software engineering tasks, including refactoring, testing, code review, and …
usage in various software engineering tasks, including refactoring, testing, code review, and …
Large language models in fault localisation
Large Language Models (LLMs) have shown promise in multiple software engineering tasks
including code generation, code summarisation, test generation and code repair. Fault …
including code generation, code summarisation, test generation and code repair. Fault …
[PDF][PDF] CodePori: Large-Scale System for Autonomous Software Development Using Multi-Agent Technology
ABSTRACT Large Language Models (LLMs) and Generative Pre-trained Transformers
(GPTs) are reshaping the field of Software Engineering (SE). Existing LLM-based multi …
(GPTs) are reshaping the field of Software Engineering (SE). Existing LLM-based multi …