Current approaches to program synthesis with Large Language Models (LLMs) exhibit a" near miss syndrome": they tend to generate programs that semantically resemble the correct …
D Lo - 2023 IEEE/ACM International Conference on Software …, 2023 - ieeexplore.ieee.org
For decades, much software engineering research has been dedicated to devising automated solutions aimed at enhancing developer productivity and elevating software …
Q Zhang, C Fang, Y Xie, Y Zhang, Y Yang… - arXiv preprint arXiv …, 2023 - arxiv.org
Software Engineering (SE) is the systematic design, development, and maintenance of software applications, underpinning the digital infrastructure of our modern mainworld. Very …
J Liu, C Sha, X Peng - 2023 38th IEEE/ACM International …, 2023 - ieeexplore.ieee.org
Pre-trained code models (eg CodeBERT and CodeT5) have demonstrated their code intelligence in various software engineering tasks, such as code summarization. And full fine …
M Weyssow, A Kamanda, H Sahraoui - arXiv preprint arXiv:2403.09032, 2024 - arxiv.org
Evaluating the alignment of large language models (LLMs) with user-defined coding preferences is a challenging endeavour that requires assessing intricate textual LLMs' …
Language models can serve as a valuable tool for software developers to increase productivity. Large generative models can be used for code generation and code …