智能化时代的软件开发：拥抱大模型的正确姿势

彭鑫

doi:10.1631/FITEE.2300537

Your Location：

Home >

Browse articles >

智能化时代的软件开发：拥抱大模型的正确姿势

常规文章 | Updated：2023-10-12

- 智能化时代的软件开发：拥抱大模型的正确姿势
- Software development in the age of intelligence: embracing large language models with the right approach
- 信息与电子工程前沿（英文） 2023年24卷第11期页码：1513-1519
- Affiliations：
  
  School of Computer Science, Fudan University, Shanghai 200438, China
- Author bio：
  
  [ "Xin PENG is Professor and Deputy Dean of School of Computer Science at Fudan University, China. He received his PhD in Computer Science from Fudan University in 2006. He is Deputy Director of CCF (China Computer Federation) Technical Committee on Sof-tware Engineering. He is Co-Editor-in-Chief of Journal of Software: Evolution and Process and serves on the editorial boards of reputable journals, such as ACM Transactions on Software Engineering and Methodology, Empirical Software Engineering, and Chinese Journal of Software. His research interests include intelligent software development, cloud native and artificial intelligence for IT operations (AIOps), and software development and testing for smart vehicle. His works won the Best Paper Award of ICSM 2011, the ACM SIGSOFT Distinguished Paper Award of ASE 2018/2021 and ICPC 2022, the IEEE TCSE Distinguished Paper Award of ICSME 2018/2019/2020 and SANER 2023, and IEEE Transactions on Software Engineering Best Paper Award for 2018." ]
- Funds：
- DOI：10.1631/FITEE.2300537
  中图分类号：
- 纸质出版日期：2023-11-0 ，
  
  收稿日期：2023-08-08，
  
  录用日期：2023-09-25
- Accepted：
Scan QR Code
彭鑫. 智能化时代的软件开发：拥抱大模型的正确姿势[J]. 信息与电子工程前沿（英文）, 2023,24(11):1513-1519.

XIN PENG. Software development in the age of intelligence: embracing large language models with the right approach. [J]. Frontiers of information technology & electronic engineering, 2023, 24(11): 1513-1519.
彭鑫. 智能化时代的软件开发：拥抱大模型的正确姿势[J]. 信息与电子工程前沿（英文）, 2023,24(11):1513-1519. DOI： 10.1631/FITEE.2300537.

XIN PENG. Software development in the age of intelligence: embracing large language models with the right approach. [J]. Frontiers of information technology & electronic engineering, 2023, 24(11): 1513-1519. DOI： 10.1631/FITEE.2300537.

摘要

以ChatGPT为代表的大语言模型技术对包括软件工程在内的很多领域都带来巨大冲击，也引发广泛焦虑。为在迷雾中看清一点方向，近期我们基于各种技术文献和实践分享以及我们自身的初步探索不断讨论和思考“大模型时代的软件工程”或者“大模型的软件开发能力”这一命题。同时我也参加了几次线上访谈，触发了更多认识和思考，在此基础上撰写了此篇文章，希望与大家分享一些观点并激发相关讨论。由于到目前为止大模型在很大程度上仍然是一个黑盒，并且大模型技术还在快速迭代和发展之中，同时目前看到的以及我们自己实践的基于大模型的软件开发案例还比较初步，因此本文的很多认识和思考不一定准确，未来还可能会随着技术和实践的发展而不断刷新。

Abstract

关键词

大语言模型ChatGPT软件工程软件开发

Keywords

references

JrBrooks FP, 1987. No silver bullet essence and accidents of software engineering. Computer, 20(4):10-19. https://doi.org/10.1109/MC.1987.1663532https://doi.org/10.1109/MC.1987.1663532

Dou SH, Shan JJ, Jia HX, et al., 2023. Towards understanding the capability of large language models on code clone detection: a survey. https://arxiv.org/abs/2308.01191https://arxiv.org/abs/2308.01191

Du XY, Liu MW, Wang KX, et al., 2023. ClassEval: a manually-crafted benchmark for evaluating LLMs on class-level code generation. https://arxiv.org/abs/2308.01861https://arxiv.org/abs/2308.01861

Hou XY, Zhao YJ, Liu Y, et al., 2023. Large language models for software engineering: a systematic literature review. https://arxiv.org/abs/2308.10620https://arxiv.org/abs/2308.10620

Liu JW, Xia CS, Wang YY, et al., 2023. Is your code generated by ChatGPT really correct? Rigorous evaluation of large language models for code generation. http://arxiv.org/abs/2305.01210http://arxiv.org/abs/2305.01210

Meyer B, 2023. AI does not help programmers. Commun ACM, early access.

Open AI, 2023. GPT-4 technical report. https://arxiv.org/abs/2303.08774https://arxiv.org/abs/2303.08774

Wang JJ, Huang YC, Chen CY, et al., 2023. Software testing with large language model: survey, landscape, and vision. https://arxiv.org/abs/2307.07221https://arxiv.org/abs/2307.07221

Welsh M, 2023. The end of programming. Commun ACM, 66(1):34-35. https://doi.org/10.1145/3570220https://doi.org/10.1145/3570220

Wu QY, Bansal G, Zhang JY, et al., 2023. AutoGen: enabling next-Gen LLM applications via multi-agent conversation. https://arxiv.org/abs/2308.08155https://arxiv.org/abs/2308.08155

Yuan ZQ, Liu JW, Zi QC, et al., 2023a. Evaluating instruction-tuned large language models on code comprehension and generation. https://arxiv.org/abs/2308.01240https://arxiv.org/abs/2308.01240

Yuan ZQ, Lou YL, Liu MW, et al., 2023b. No more manual tests? Evaluating and improving ChatGPT for unit test generation. https://arxiv.org/abs/2305.04207https://arxiv.org/abs/2305.04207

Zhao WX, Zhou K, Li JY, et al., 2023. A survey of large language models. https://arxiv.org/abs/2303.18223https://arxiv.org/abs/2303.18223

Zheng ZB, Ning KW, Chen JC, et al., 2023. Towards an understanding of large language models in software engineering tasks. https://arxiv.org/abs/2308.11396https://arxiv.org/abs/2308.11396

浏览量

Downloads

CSCD

文章被引用时，请邮件提醒。

Submit

工具集

关联资源

Four development stages of collective intelligence

An experimental study on the conversion between IFPUG and UCP functional size measurement units