A Hybrid Prompting-based Code Generation on Software Development Life Cycle 


Vol. 15,  No. 3, pp. 230-237, Mar.  2026
https://doi.org/10.3745/TKIPS.2026.15.3.230


PDF
  Abstract

The advancement of large language models (LLMs) is transforming software development. However, LLMs struggle to accurately interpret user intent when insufficient context and requirements are provided. As a result, developers must invest significant effort in advanced prompt engineering to achieve the desired outcomes. To solve this, we propose a hybrid code generation mechanism that takes natural language requirements, design information, and template code as input. By providing a predefined template that represents the customer's intent and the system's structure, the method enables LLMs to understand specific requirements more accurately. This approach is expected to improve the accuracy and reliability of code generation compared to natural language-only methods. This study objectively evaluates its performance in comparison to existing LLM approaches through a case study. By presenting a new paradigm for LLM-based software development, the proposed method is expected to offer both academic and practical contributions to the field.

  Statistics
  Cite this article

[IEEE Style]

Y. Jin, J. Kim, K. Kim, R. Y. C. Kim, "A Hybrid Prompting-based Code Generation on Software Development Life Cycle," The Transactions of the Korea Information Processing Society, vol. 15, no. 3, pp. 230-237, 2026. DOI: https://doi.org/10.3745/TKIPS.2026.15.3.230.

[ACM Style]

Yejin Jin, Janghwan Kim, Kidu Kim, and R. Young Chul Kim. 2026. A Hybrid Prompting-based Code Generation on Software Development Life Cycle. The Transactions of the Korea Information Processing Society, 15, 3, (2026), 230-237. DOI: https://doi.org/10.3745/TKIPS.2026.15.3.230.

Forms

Search
(IN TITLE, AUTHOR, ABSTRACT,KEYWORDS)

Advanced Search ▼

POPULAR KEYWORDS
(TOP 10 KEYWORDS)

Recent Publications
(LAST 3 YEARS)

Old Journals

Indexing

All publications of TKIPS is indexed in DOI, EBSCO, Google Scholar, Crossref, and CrossCheck.

TKIPS is also selected as the Journal for Accreditation by NRF (National Research Foundation of Korea).

Related Journals