OVERVIEW OF APPLICATION OF GENERATIVE ARTIFICIAL INTELLIGENCE IN SOFTWARE SOURCE CODE GENERATION

Nguyễn Văn Việt; Nguyễn Hữu Khánh; Nguyễn Thế Vịnh; Vũ Văn Diện; Nguyễn Kim Sơn; Lương Thị Minh Huế

doi:10.34238/tnu-jst.12305

OVERVIEW OF APPLICATION OF GENERATIVE ARTIFICIAL INTELLIGENCE IN SOFTWARE SOURCE CODE GENERATION

About this article

Received: 13/03/25 Revised: 26/06/25 Published: 28/06/25

Authors

1. Nguyen Van Viet , TNU of Information and Communication Technology
2. Nguyen Huu Khanh, Thai Nguyen University
3. Nguyen The Vinh, TNU of Information and Communication Technology
4. Vu Van Dien, TNU of Information and Communication Technology
5. Nguyen Kim Son, TNU of Information and Communication Technology
6. Luong Thi Minh Hue, TNU of Information and Communication Technology

Abstract

This paper provides an overview of the application of generative artificial intelligence in the process of software source code generation. Large language models such as GPT-4, CodeBERT, Codex, and AlphaCode are helping programmers automate many tasks, including generating code from natural language descriptions, detecting programming errors, optimizing code, and improving software maintainability. The study uses the PRISMA method to analyze scientific literature from Web of Science during 2021-2025, focusing on important topics and research trends of Large language models in software engineering. The results show that the number of articles on this topic increased sharply in 2024, reflecting the growing interest in artificial intelligence in software development. The studies also show that Elsevier and IEEE are the two sources of documents with the largest number of publications in this field. Although generative artificial intelligence offers many benefits, the study also addresses important challenges such as code accuracy, error detection, security and privacy issues. Integrating generative artificial intelligence into the software development process requires appropriate approaches to exploit the full potential of this technology. The paper concludes that research on Large language models in software engineering still has many gaps, opening up opportunities for new directions of development in the future.

Keywords

Generative artificial intelligence; Software engineering; Transformer; Artificial intelligence; PRISMA

Full Text:

PDF (Tiếng Việt)

References

[1] Y. Wan et al., “Deep learning for code intelligence: Survey, benchmark and toolkit,” ACM Comput. Surv., vol. 56, no. 12, pp. 1–41, 2024.

[2] J. Wang, Y. Huang, C. Chen, Z. Liu, S. Wang, and Q. Wang, “Software testing with large language models: Survey, landscape, and vision,” IEEE Transactions on Software Engineering, vol. 50, no. 4, pp. 911 – 936, 2024.

[3] Z. Zheng et al., “Towards an understanding of large language models in software engineering tasks,” Empirical Softw. Engg., vol. 30, no. 2, Dec. 2024, doi: 10.1007/s10664-024-10602-0.

[4] V. V. Nguyen et al., “Revolutionizing Education: An Extensive Analysis of Large Language Models Integration,” IRJSTEM, vol. 4, no. 4, pp. 10-21, 2024.

[5] H. K. Nguyen, V. V. Nguyen, T. V. Nguyen, and H. C. Nguyen, “Phi-3 Meets Law: Fine-tuning Mini Language Models for Legal Document Understanding,” Research, Development and Application on Information and Communication Technology, vol. 2024, no. 3, pp. 136–142, 2024.

[6] D. Song et al., “LUNA: A Model-Based Universal Analysis Framework for Large Language Models,” IEEE Transactions on Software Engineering, vol. 50, no. 7, pp. 1921–1948, 2024, doi: 10.1109/TSE.2024.3411928.

[7] S. S. Sohail et al., “Decoding ChatGPT: A taxonomy of existing research, current challenges, and possible future directions,” Journal of King Saud University-Computer and Information Sciences, vol. 35, no. 8, 2023, Art. no. 101675.

[8] N. Kiesler, D. Lohr, and H. Keuning, “Exploring the potential of large language models to generate formative programming feedback,” in 2023 IEEE Frontiers in Education Conference (FIE), IEEE, 2023, pp. 1–5.

[9] Z. Fan, X. Gao, M. Mirchev, A. Roychoudhury, and S. H. Tan, “Automated repair of programs from large language models,” in 2023 IEEE/ACM 45th International Conference on Software Engineering (ICSE), IEEE, 2023, pp. 1469–1481.

[10] J. Lu, L. Yu, X. Li, L. Yang, and C. Zuo, “LLaMA-Reviewer: Advancing Code Review Automation with Large Language Models through Parameter-Efficient Fine-Tuning,” in 2023 IEEE 34th International Symposium on Software Reliability Engineering (ISSRE), IEEE, 2023, pp. 647–658.

[11] V. Siddeshwar, S. Alwidian, and M. Makrehchi, “A Systematic Review of AI-Enabled Frameworks in Requirements Elicitation,” IEEE Access, vol. 12, pp. 154310-154336, 2024.

[12] J. Wei et al., “Emergent abilities of large language models,” arXiv preprint arXiv:2206.07682, 2022.

[13] J. Sallou, T. Durieux, and A. Panichella, “Breaking the silence: the threats of using llms in software engineering,” in Proceedings of the 2024 ACM/IEEE 44th International Conference on Software Engineering: New Ideas and Emerging Results, 2024, pp. 102–106.

[14] G. Xiao, J. Lin, M. Seznec, H. Wu, J. Demouth, and S. Han, “Smoothquant: Accurate and efficient post-training quantization for large language models,” in International Conference on Machine Learning, PMLR, 2023, pp. 38087–38099.

[15] Y. Liu et al., “Summary of chatgpt-related research and perspective towards the future of large language models,” Meta-Radiology, vol. 1, no. 2, 2023, Art. no. 100017.

[16] P. Vaithilingam, T. Zhang, and E. L. Glassman, “Expectation vs. experience: Evaluating the usability of code generation tools powered by large language models,” in Chi Conference on Human Factors in Computing Systems Extended Abstracts, 2022, pp. 1–7.

[17] I. Singh et al., “Progprompt: Generating situated robot task plans using large language models,” in 2023 IEEE International Conference on Robotics and Automation (ICRA), IEEE, 2023, pp. 11523–11530.

[18] S. Makridakis, F. Petropoulos, and Y. Kang, “Large language models: Their success and impact,” Forecasting, vol. 5, no. 3, pp. 536–549, 2023.

[19] Y. Fu et al., “Gpt4aigchip: Towards next-generation ai accelerator design automation via large language models,” in 2023 IEEE/ACM International Conference on Computer Aided Design (ICCAD), IEEE, 2023, pp. 1–9.

DOI: https://doi.org/10.34238/tnu-jst.12305

Refbacks

There are currently no refbacks.



Remember me