DOI - Vydavatelství Mendelovy univerzity v Brně

Identifikátory DOI

DOI: 10.11118/978-80-7701-047-4-0029

OPTIMIZING PROMPTS THROUGH AI FRAMEWORKS: A PATH TO MORE RELEVANT RESPONSES

Jana Dannhoferová1, Petr Jedlička1
1 Department of Informatics, Faculty of Business and Economics, Mendel University in Brno, Zemědělská 1, 613 00 Brno, Czech Republic

The rapid growth of large language models has increased the importance of prompt engineering in facilitating effective human-computer interaction. While various frameworks have been developed to assist users with prompt engineering, a comparative analysis of these frameworks and their core components is still lacking. This study addresses this gap by analyzing key terms in widely used frameworks such as RACEF (Role, Audience, Context, Example, Format) to identify recurring elements that are critical to prompt optimization. The findings will lead to actionable recommendations and the development of a unified framework incorporating the most important elements for effective prompt engineering.

Klíčová slova: artificial intelligence, prompt engineering, frameworks, core components

stránky: 29-38, online: 2025



Reference

  1. Allton, M. 2024. Prompt Engineering Made Easy: The RICCE Framework for AI Content Writing. [Accessed 2024, December 20] https://www.thesocialmediahat.com/blog/prompt-engineering-made-easy-the-ricce-framework-for-ai-content-writing/
  2. Amatriain, X. 2024. Prompt Design and Engineering: Introduction and Advanced Methods. arXiv preprint. arXiv:2401.14423.
  3. Bang, Y., Cahyawijaya, S., Lee, N., Dai, W., Su, D., Wilie, B., Lovenia, H., Ji, Z., Yu, T., Chung, W., Do, Q. V., Xu, Y., Fung, P. 2023. A multitask, multilingual, multimodal evaluation of ChatGPT on reasoning, hallucination, and interactivity. arXiv preprint. arXiv:2302.04023. https://doi.org/10.48550/arXiv.2302.04023 Přejít k původnímu zdroji...
  4. Cheng, F., Zouhar, V., Arora, S., Sachan, M., Strobelt, H., El-Assady, M. 2023. RELIC: Investigating large language model responses using self-consistency. arXiv preprint. arXiv:2311.16842. https://doi.org/10.48550/arXiv.2311.16842. Přejít k původnímu zdroji...
  5. Juuzt. 2025. Streamlining AI Prompt Engineering with the RASCEF Framework. [Accessed 2025, January 10] https://juuzt.ai/knowledge-base/prompt-frameworks/the-rascef-framework/
  6. Korzynski, P., Mazurek, G., Krzypkowska, P., Kurasinski, A. 2023. Artificial intelligence prompt engineering as a new digital competence: Analysis of generative AI technologies such as ChatGPT. Entrepreneurial Business and Economics Review. 11(3), 25-37. https://doi.org/10.15678/EBER.2023.110302 Přejít k původnímu zdroji...
  7. Lu, Y., Bartolo, M., Moore, A., Riedel, S., Stenetorp, P. 2022. Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivity. In: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics. Volume 1: Long Papers. Dublin, Ireland: Association for Computational Linguistics, pages 8086-8098. https://doi.org/10.18653/v1/2022.acl-long.556 Přejít k původnímu zdroji...
  8. Moran, K. 2024. CARE: Structure for Crafting AI Prompts. [Accessed 2024, December 10] https://www.nngroup.com/articles/careful-prompts/
  9. Ouyang, L., Wu, J., Jiang, X., Almeida, D., Wainwright, C.L., Mishkin, P., Zhang, C., Agarwal, S., Slama, K., Ray, A. et al. 2022. Training language models to follow instructions with human feedback. arXiv preprint. arXiv:2203.02155.
  10. Ozturk, A. 2025. Another Prompting Framework: RACE (Role, Action, Context, Execute). [Accessed 2025, May 16] https://drayseozturk.org/2025/02/22/another-prompting-framework-race-role-action-context-execute/
  11. Partelow, S. 2023. What is a framework? Understanding their purpose, value, development and use., Journal of Environmental Studies and Sciences. 13, 510-519. https://doi.org/10.1007/s13412-023-00833-w Přejít k původnímu zdroji...
  12. Reynolds, L., McDonell, K. 2021. Prompt programming for large language models: Beyond the few-shot paradigm. Paper presented at the Extended Abstracts of the 2021 CHI Conference on Human Factors in Computing Systems. arXiv:2102.07350. https://doi.org/10.48550/arXiv.2102.07350 Přejít k původnímu zdroji...
  13. Saleem, M. 2024. 11 ChatGPT Prompt Frameworks Every Marketer Should Know. [Accessed 2024, September 30] https://buttercms.com/blog/chatgpt-prompt-frameworks/
  14. Schulhoff, S., Ilie, M., Balepur, N., Kahadze, K., Liu, A., Si, C., Li, Y., Gupta, A., Han, H., Schulhoff, S., Dulepet, P. S., Vidyadhara, S., Ki, D., Agrawal, S., Pham, C., Kroiz, G., Li, F., Tao, H., Srivastava, A., Da Costa, H., Gupta, S., Rogers, M. L., Goncearenco, I., Sarli, G., Galynker, I., Peskoff, D., Carpuat, M., White, J., Anadkat, S., Hoyle, A., Resnik, P. 2024. The Prompt Report: A Systematic Survey of Prompting Techniques. arXiv preprint arXiv: arXiv:2406.06608. https://doi.org/0.48550/arXiv.2406.06608
  15. Song, W., Liyan, T., Akash, M., Justin, F. R., George, S., Ying, D., Yifan, P. 2022. Trustworthy assertion classification through prompting. Journal of Biomedical Informatics. 132, 104139. ISSN 1532-0464. https://doi.org/10.1016/j.jbi.2022.104139 Přejít k původnímu zdroji...
  16. Wei, J., Wang, X., Schuurmans, D., Bosma, M., Ichter, B., Xia, F., Chi, E. H., Le, Q. V., Zhou, D. 2022. Chain-of-Thought Prompting Elicits Reasoning in Large Language Models. arXiv preprint. arXiv:2201.11903v6. https://doi.org/10.48550/arXiv.2201.11903. Přejít k původnímu zdroji...
  17. Zahid, E. 2024. How to get ChatGPT to Roleplay. [Accessed 2025, January 3] https://xpertprompt.com/2024/07/15/how-to-get-chatgpt-to-roleplay/
  18. Zamfirescu-Pereira, J., Wong, R. Y., Hartmann, B., Yang, Q. 2023. Why johnny can't prompt: How non-ai experts try (and fail) to design LLM prompts. In: Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems. New York, USA: Association for Computing Machinery. ISBN 9781450394215. https://doi.org/10.1145/3544548.3581388 Přejít k původnímu zdroji...