A survey of large language models for code: Evolution, benchmarking, and future trends

Z Zheng, K Ning, Y Wang, J Zhang, D Zheng… - arxiv preprint arxiv …, 2023 - arxiv.org
General large language models (LLMs), represented by ChatGPT, have demonstrated
significant potential in tasks such as code generation in software engineering. This has led …

[HTML][HTML] Advances and Challenges in Low-Resource-Environment Software Systems: A Survey

A Agbeyangi, H Suleman - Informatics, 2024 - mdpi.com
A low-resource environment has limitations in terms of resources, such as limited network
availability and low-powered computing devices. In such environments, it is arguably more …

Learning agent-based modeling with LLM companions: Experiences of novices and experts using ChatGPT & NetLogo chat

J Chen, X Lu, Y Du, M Rejtig, R Bagley… - Proceedings of the CHI …, 2024 - dl.acm.org
Large Language Models (LLMs) have the potential to fundamentally change the way people
engage in computer programming. Agent-based modeling (ABM) has become ubiquitous in …

The potential of LLMs for coding with low-resource and domain-specific programming languages

A Tarassow - arxiv preprint arxiv:2307.13018, 2023 - arxiv.org
This paper presents a study on the feasibility of using large language models (LLM) for
coding with low-resource and domain-specific programming languages that typically lack …

Automatic detection of llm-generated code: A case study of claude 3 haiku

M Rahman, SH Khatoonabadi, A Abdellatif… - arxiv preprint arxiv …, 2024 - arxiv.org
Using Large Language Models (LLMs) has gained popularity among software developers
for generating source code. However, the use of LLM-generated code can introduce risks of …

Investigating the transferability of code repair for low-resource programming languages

K Wong, A Amayuelas, L Pan, WY Wang - arxiv preprint arxiv:2406.14867, 2024 - arxiv.org
Large language models (LLMs) have shown remarkable performance on code generation
tasks. A recent use case is iterative code repair, where an LLM fixes an incorrect program by …

Non-Autoregressive Line-Level Code Completion

F Liu, Z Fu, G Li, Z **, H Liu, Y Hao… - ACM Transactions on …, 2024 - dl.acm.org
Software developers frequently use code completion tools to accelerate software
development by suggesting the following code elements. Researchers usually employ …