EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Automated prompt generation with a task-oriented approach

FATİH ÖĞÜN, TUNGA GÜNGÖR

Turkish Journal of Electrical Engineering and Computer Sciences · 13.11.2026 · 34 (6) · 1169-1188

DOI: 10.55730/1300-0632.4295 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Turkish Journal of Electrical Engineering and Computer Sciences, online erschienen am 13.11.2026. Verfasst von FATİH ÖĞÜN und 1 weiteren Autor:innen. Die Arbeit nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

With the introduction and fast growth of large language models (LLMs), designing detailed and effective prompts has become critical. Human-designed prompts are often time-consuming to produce and error-prone. Designing and developing prompts automatically with the help of LLMs has the potential to facilitate this process with improved results. Achieving fast and high-quality prompt development and integrating with the content generation process of LLMs is an important milestone in LLM-based content generation. In this paper, we use a content development framework, HybridGen, to generate prompts automatically based on given objectives. HybridGen is a multiagent framework with parametric setup and with a shared workbench. We use a novel iterative approach with the aim of creating a detailed multisection prompt converging to given objectives. We assess the proposed approach using both quality evaluation and task-based evaluation. The results show that the automatically generated prompts perform better than the manual prompts and increase the performance of small-size LLMs making them comparable to larger LLMs.

Zitieren

APA

ÖĞÜN, F., & GÜNGÖR, T. (2026). Automated prompt generation with a task-oriented approach. Turkish Journal of Electrical Engineering and Computer Sciences, 34(6), 1169-1188. https://doi.org/10.55730/1300-0632.4295

Vancouver

ÖĞÜN F, GÜNGÖR T. Automated prompt generation with a task-oriented approach. Turkish Journal of Electrical Engineering and Computer Sciences. 2026;34(6):1169-1188. doi:10.55730/1300-0632.4295

BibTeX
@article{N2026,
  author = {ÖĞÜN, FATİH and GÜNGÖR, TUNGA},
  title = {Automated prompt generation with a task-oriented approach},
  journal = {Turkish Journal of Electrical Engineering and Computer Sciences},
  year = {2026},
  volume = {34},
  number = {6},
  pages = {1169--1188},
  doi = {10.55730/1300-0632.4295}
}
Kostenlos starten →