The task of generating code from a natural language description, or NL2Code, is considered a pressing and significant challenge in code intelligence. Thanks to the rapid development …
H Yu, B Shen, D Ran, J Zhang, Q Zhang, Y Ma… - Proceedings of the 46th …, 2024 - dl.acm.org
Code generation models based on the pre-training and fine-tuning paradigm have been increasingly attempted by both academia and industry, resulting in well-known industrial …
Code intelligence leverages machine learning techniques to extract knowledge from extensive code corpora, with the aim of developing intelligent tools to improve the quality …
B Shen, J Zhang, T Chen, D Zan, B Geng, A Fu… - arXiv preprint arXiv …, 2023 - arxiv.org
Large Language Models for Code (Code LLM) are flourishing. New and powerful models are released on a weekly basis, demonstrating remarkable performance on the code …
X Du, M Liu, K Wang, H Wang, J Liu, Y Chen… - arXiv preprint arXiv …, 2023 - arxiv.org
In this work, we make the first attempt to evaluate LLMs in a more challenging code generation scenario, ie class-level code generation. We first manually construct the first …
X Ren, P Zhou, X Meng, X Huang, Y Wang… - arXiv preprint arXiv …, 2023 - arxiv.org
The scaling of large language models has greatly improved natural language understanding, generation, and reasoning. In this work, we develop a system that trained a …
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 …
Z Yang, S Chen, C Gao, Z Li, G Li, R Lv - arXiv preprint arXiv:2303.01056, 2023 - arxiv.org
Code Generation aims at generating relevant code fragments according to given natural language descriptions. In the process of software development, there exist a large number of …
The introduction of large language models has significantly advanced code generation. However, open-source models often lack the execution capabilities and iterative refinement …