Principles of requests’ formulation to artificial intelligence technologies as a component of interaction strategies
https://doi.org/10.20310/1810-0201-2025-30-5-1083-1090
Abstract
Importance. In light of the rapid integration of artificial intelligence (AI) systems in both practical and research applications, the formulation of queries assumes a pivotal role in human–machine interaction strategies. This article delves into the realm of Large Language Models (LLMs) and systematically explores effective prompting principles, highlighting their significance in enhancing the accuracy, consistency, and controllability of AI-generated outputs. Our objective is to construct a comprehensive taxonomy of query types within the framework of interaction strategies.
Materials and Methods. To accomplish this, we employ methods of analysis and synthesis of existing theoretical and practical materials related to this subject. These materials are drawn from studies conducted over the past three years, exploring various approaches to optimizing human–machine communication.
Results and Discussion. The findings of the investigation reveal that there exist several types of inquiries at the initial phase of engagement with the model. Following these queries, a dialogue ensues to validate the accuracy of the provided responses. The algorithm for effective interaction with the machine necessitates specific skills that can be evaluated based on specific criteria and the metrics of the obtained response.
Conclusion. Establishing standardization for query generation processes is crucial for ensuring the secure and responsible utilization of AI in large-scale applications. Consequently, the development of interdisciplinary programs focused on crafting strategies for interacting with AI should be prioritized in future research endeavors.
About the Author
A. P. Avramenko
Lomonosov Moscow State University
Россия
Россия
Anna P. Avramenko, Cand. Sci. (Education), Associate Professor of the Linguistics and Information Technologies Department, Faculty of Foreign Languages and Area Studies
RSCI AuthorID: 839847
Scopus Author ID: 57221929626
1 Leninskiye Gory, Moscow, 119991
References
1. Korzynski, P., Mazurek, G., Krzypkowska, P., & Kurasniski, A. Artificial intelligence prompt engineering as a new digital competence: Analysis of generative AI technologies such as ChatGPT // Entrepreneurial Business and Economics Review, 2023. 11(3). P. 25–37. https://doi.org/10.15678/EBER.2023.110302
2. Sysoev P.V. Kompetenciya sovremennogo pedagoga v oblasti iskusstvennogo intellekta: struktura i soderzhanie // Vysshee obrazovanie v Rossii, 2025. T. 34. No 6. S. 58–79. DOI: 10.31992/0869-3617-2025-34-6-58-79
3. Fox Tree, J., Herring, S. C., Nguyen, A., Whittaker, S., Martin, R., & Takayama, L. Conversational fluency and attitudes towards robot pilots in telepresence robot-mediated interaction // Journal of Computer Supported Cooperative Work, 2024. 33. P. 473–498.
4. Council of Europe. Common European Framework of Reference for Languages: Learning, Teaching, Assessment – Companion volume // Council of Europe Publishing, Strasbourg, 2020. URL: https://www.coe.int/lang-cefr
5. Oppenlaender, J. A Taxonomy of Prompt Modifiers for Text‑to‑Image Generation // arXiv preprint, 2022. arXiv:2204.13988. https://doi.org/10.48550/arXiv.2204.13988
6. Si, C., et al. Prompting GPT‑3 to Be Reliable // arXiv preprint, 2022. arXiv:2210.09150.
7. Cao, Y. T., Pruksachatkun, Y., Chang, K.-W., Gupta, R., Kumar, V., Dhamala, J., & Galstyan, A. On the intrinsic and extrinsic fairness evaluation metrics for contextualized language representations // Proceedings of the ACL, 2022.
8. Ekin, S. Prompt Engineering for ChatGPT: A Quick Guide to Techniques, Tips, and Best Practices // TechRxiv, 2023. https://doi.org/10.36227/techrxiv.22683919.v2
9. Kovari, A., et al. ChatGPT the Omniscient? A Guide to Effective Prompting // 2024 IEEE 7th International Conference and Workshop Óbuda on Electrical and Power Engineering (CANDO‑EPE), 2024. Pp. 000047–000052. https://doi.org/10.1109/CANDO-EPE65072.2024.10772984
10. Kim, J., et al. Which Is Better? Exploring Prompting Strategy for LLM‑based Metrics // arXiv preprint, 2023. abs/2311.03754. https://doi.org/10.48550/arXiv.2311.03754
11. Bhandari, P., et al. A Survey on Prompting Techniques in LLMs // Technical report/preprint, 2023.
12. Fagbohun, O., et al. An Empirical Categorization of Prompting Techniques for Large Language Models: A Practitioner's Guide // arXiv preprint, 2024. abs/2402.14837. https://doi.org/10.48550/arXiv.2402.14837
13. Avramenko, A.P., Matveeva, O.YU. Opredelenie urovnya vladeniya strategiyami kommunikativnogo vzaimodejstviya u studentov magistratury neyazykovyh fakul'tetov (francuzskij yazyk) // Rhema, 2020. № 3. P. 53–64.
14. Yu, Z., et al. Towards Better Chain‑of‑Thought Prompting Strategies: A Survey // arXiv preprint, 2023. abs/2310.04959. https://doi.org/10.48550/arXiv.2310.04959
15. Chang, E. Y. Prompting Large Language Models with the Socratic Method // 2023 IEEE 13th Annual Computing and Communication Workshop and Conference (CCWC), Las Vegas, NV, USA, 2023. Pp. 0351–0360. https://doi.org/10.1109/CCWC57344.2023.10099179
Review
For citations:
Avramenko A.P. Principles of requests’ formulation to artificial intelligence technologies as a component of interaction strategies. Tambov University Review. Series: Humanities. 2025;30(5):1083-1090. https://doi.org/10.20310/1810-0201-2025-30-5-1083-1090
Views:
91
JATS XML
Email this article 