Large language models for software engineering: A systematic literature review
Large Language Models (LLMs) have significantly impacted numerous domains, including
Software Engineering (SE). Many recent publications have explored LLMs applied to …
Software Engineering (SE). Many recent publications have explored LLMs applied to …
Octopack: Instruction tuning code large language models
Finetuning large language models (LLMs) on instructions leads to vast performance
improvements on natural language tasks. We apply instruction tuning using code …
improvements on natural language tasks. We apply instruction tuning using code …
A survey of large language models for code: Evolution, benchmarking, and future trends
General large language models (LLMs), represented by ChatGPT, have demonstrated
significant potential in tasks such as code generation in software engineering. This has led …
significant potential in tasks such as code generation in software engineering. This has led …
The formai dataset: Generative ai in software security through the lens of formal verification
This paper presents the FormAI dataset, a large collection of 112,000 AI-generated
compilable and independent C programs with vulnerability classification. We introduce a …
compilable and independent C programs with vulnerability classification. We introduce a …
BioCoder: a benchmark for bioinformatics code generation with contextual pragmatic knowledge
Pre-trained language models like ChatGPT have significantly improved code generation. As
these models scale up, there is an increasing need for the output to handle more intricate …
these models scale up, there is an increasing need for the output to handle more intricate …
A survey on large language models for software engineering
Software Engineering (SE) is the systematic design, development, and maintenance of
software applications, underpinning the digital infrastructure of our modern mainworld. Very …
software applications, underpinning the digital infrastructure of our modern mainworld. Very …
Repohyper: Better context retrieval is all you need for repository-level code completion
Code Large Language Models (CodeLLMs) have demonstrated impressive proficiency in
code completion tasks. However, they often fall short of fully understanding the extensive …
code completion tasks. However, they often fall short of fully understanding the extensive …
Ratgpt: Turning online llms into proxies for malware attacks
M Beckerich, L Plein, S Coronado - arXiv preprint arXiv:2308.09183, 2023 - arxiv.org
The evolution of Generative AI and the capabilities of the newly released Large Language
Models (LLMs) open new opportunities in software engineering. However, they also lead to …
Models (LLMs) open new opportunities in software engineering. However, they also lead to …
LLMs in Web Development: Evaluating LLM-Generated PHP Code Unveiling Vulnerabilities and Limitations
This study evaluates the security of web application code generated by Large Language
Models, analyzing 2,500 GPT-4 generated PHP websites. These were deployed in Docker …
Models, analyzing 2,500 GPT-4 generated PHP websites. These were deployed in Docker …
BioCoder: a benchmark for bioinformatics code generation with large language models
X Tang, B Qian, R Gao, J Chen, X Chen… - …, 2024 - academic.oup.com
Pretrained large language models (LLMs) have significantly improved code generation. As
these models scale up, there is an increasing need for the output to handle more intricate …
these models scale up, there is an increasing need for the output to handle more intricate …