An Analytical Perspective on Software Engineering for Large Language Models

Tianlin Li, Qiang Hu, Chong Wang, Jian Zhang, Wei Ma, Aishan Liu, Jingyi Wang, Yang Liu

Abstract: Large language models (LLMs) are reshaping software and transforming software paradigms. However, developing LLMs is both costly and frequently susceptible to trustworthiness issues. In this paper, we analyze whether these issues can be effectively mitigated by applying software engineering principles. In particular, we analyze the value of applying the Waterfall Model’s phases to the LLM engineering process. We believe this study can provide valuable insights and guide the future development of LLMs toward greater cost-efficiency and trustworthiness.

External IDs:doi:10.1007/978-3-032-00828-2_28