Skip to main navigation Skip to search Skip to main content

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
  • *Corresponding author for this work
  • Nanyang Technological University
  • Tianjin University
  • Singapore Management University
  • Zhejiang University

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

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.

Original languageEnglish
Title of host publicationEngineering of Complex Computer Systems - 29th International Conference, ICECCS 2025, Proceedings
EditorsYuan Zhou, Zuohua Ding, Sin G. Teo, Xiaofei Xie, Yang Liu
PublisherSpringer Science and Business Media Deutschland GmbH
Pages489-494
Number of pages6
ISBN (Print)9783032008275
DOIs
StatePublished - 2026
Event29th International Conference on Engineering of Complex Computer Systems, ICECCS 2025 - Hangzhou, China
Duration: 2 Jul 20254 Jul 2025

Publication series

NameLecture Notes in Computer Science
Volume15746 LNCS
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

Conference29th International Conference on Engineering of Complex Computer Systems, ICECCS 2025
Country/TerritoryChina
CityHangzhou
Period2/07/254/07/25

Fingerprint

Dive into the research topics of 'An Analytical Perspective on Software Engineering for Large Language Models'. Together they form a unique fingerprint.

Cite this