Starvector: Generating scalable vector graphics code from images

JA Rodriguez, S Agarwal, IH Laradji… - arXiv preprint arXiv …, 2023 - arxiv.org
Scalable Vector Graphics (SVGs) have become integral in modern image rendering
applications due to their infinite scalability in resolution, versatile usability, and editing …

The Silicone Ceiling: Auditing GPT's Race and Gender Biases in Hiring

L Armstrong, A Liu, S MacNeil, D Metaxa - arXiv preprint arXiv:2405.04412, 2024 - arxiv.org
Large language models (LLMs) are increasingly being introduced in workplace settings,
with the goals of improving efficiency and fairness. However, concerns have arisen …

XAI for all: Can large language models simplify explainable AI?

P Mavrepis, G Makridis, G Fatouros, V Koukos… - arXiv preprint arXiv …, 2024 - arxiv.org
The field of Explainable Artificial Intelligence (XAI) often focuses on users with a strong
technical background, making it challenging for non-experts to understand XAI methods …

Just another copy and paste? Comparing the security vulnerabilities of ChatGPT generated code and StackOverflow answers

S Hamer, M d'Amorim, L Williams - 2024 IEEE Security and …, 2024 - ieeexplore.ieee.org
Sonatype's 2023 report found that 97% of developers and security leads integrate
generative Artificial Intelligence (AI), particularly Large Language Models (LLMs), into their …

Numeracy from literacy: Data science as an emergent skill from large language models

D Noever, F McKee - arXiv preprint arXiv:2301.13382, 2023 - arxiv.org
Large language models (LLM) such as OpenAI's ChatGPT and GPT-3 offer unique testbeds
for exploring the translation challenges of turning literacy into numeracy. Previous publicly …

Using large language models to generate junit tests: An empirical study

ML Siddiq, JC Da Silva Santos, RH Tanvir… - Proceedings of the 28th …, 2024 - dl.acm.org
A code generation model generates code by taking a prompt from a code comment, existing
code, or a combination of both. Although code generation models (eg, GitHub Copilot) are …

Commit Messages in the Age of Large Language Models

CV Lopes, VI Klotzman, I Ma, I Ahmed - arXiv preprint arXiv:2401.17622, 2024 - arxiv.org
Commit messages are explanations of changes made to a codebase that are stored in
version control systems. They help developers understand the codebase as it evolves …

Exploring the verifiability of code generated by github copilot

D Wong, A Kothig, P Lam - arXiv preprint arXiv:2209.01766, 2022 - arxiv.org
GitHub's Copilot generates code quickly. We investigate whether it generates good code.
Our approach is to identify a set of problems, ask Copilot to generate solutions, and attempt …

Toward Artificial Intelligence-Human Paired Programming: A Review of the Educational Applications and Research on Artificial Intelligence Code-Generation Tools

J Liu, S Li - Journal of Educational Computing Research, 2024 - journals.sagepub.com
Pair Programming is considered an effective approach to programming education, but the
synchronous collaboration of two programmers involves complex coordination, making this …

Astraios: Parameter-Efficient Instruction Tuning Code Large Language Models

TY Zhuo, A Zebaze, N Suppattarachai… - arXiv preprint arXiv …, 2024 - arxiv.org
The high cost of full-parameter fine-tuning (FFT) of Large Language Models (LLMs) has led
to a series of parameter-efficient fine-tuning (PEFT) methods. However, it remains unclear …