EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

User-Centered Prompt Strategy Evaluation for Large Language Model Interaction

Daphne Poon

INTERNATIONAL JOURNAL OF RESEARCH & SOCIAL SCIENCES · 30.07.2026 · 6 (2) · 1-12

DOI: 10.66238/ijrss.v6i2.117 ↗

Kurz gefasst

Fachartikel in der Zeitschrift INTERNATIONAL JOURNAL OF RESEARCH & SOCIAL SCIENCES, online erschienen am 30.07.2026. Verfasst von Daphne Poon. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The integration of large language models into everyday computing environments has fundamentally transformed human-computer interaction, shifting the paradigm from deterministic command-line operations to probabilistic natural language discourse. As these models become ubiquitous, the strategies users employ to communicate their intents, commonly known as prompt engineering, have emerged as a critical determinant of system efficacy and user satisfaction. This paper presents a comprehensive, user-centered evaluation of various prompt strategies utilized in large language model interactions. By shifting the analytical focus from purely computational benchmarks to human-centric usability metrics, this research systematically investigates how different prompting techniques impact cognitive load, task completion efficiency, and overall user trust. Through a meticulously designed empirical study involving diverse participant demographics and multifaceted task scenarios, we construct a taxonomy of user intents and map them to optimal prompting frameworks. The findings reveal that while highly structured, multi-step prompt strategies yield superior technical outputs, they inadvertently impose substantial cognitive burdens on novice users, thereby reducing interaction fluidity. Conversely, adaptive prompting systems that dynamically scaffold user inputs demonstrate significant potential in bridging the gap between technical complexity and user accessibility. This study ultimately advocates for the integration of adaptive assistance mechanisms within user interfaces, providing actionable guidelines for developers to enhance the accessibility and reliability of conversational artificial intelligence agents in generalized domains.

Zitieren

APA

Poon, D. (2026). User-Centered Prompt Strategy Evaluation for Large Language Model Interaction. INTERNATIONAL JOURNAL OF RESEARCH & SOCIAL SCIENCES, 6(2), 1-12. https://doi.org/10.66238/ijrss.v6i2.117

Vancouver

Poon D. User-Centered Prompt Strategy Evaluation for Large Language Model Interaction. INTERNATIONAL JOURNAL OF RESEARCH & SOCIAL SCIENCES. 2026;6(2):1-12. doi:10.66238/ijrss.v6i2.117

BibTeX
@article{Poon2026,
  author = {Poon, Daphne},
  title = {User-Centered Prompt Strategy Evaluation for Large Language Model Interaction},
  journal = {INTERNATIONAL JOURNAL OF RESEARCH & SOCIAL SCIENCES},
  year = {2026},
  volume = {6},
  number = {2},
  pages = {1--12},
  doi = {10.66238/ijrss.v6i2.117}
}
Kostenlos starten →