The art of prompts' formulation: limitations, potential, and practical examples in large language models

Authors

DOI:

https://doi.org/10.56294/saludcyt2024.969

Keywords:

prompt engineering, Language models, Personalized responses, AI quality, AI interaction

Abstract

Introduction: "prompt engineering" is crucial in the use of AI models like GPT-3 and GPT-4, as it helps obtain effective responses in areas such as text generation and programming. A well-crafted prompt improves the quality of the responses. The study analyzed how LLMs function and gathered advice for prompt engineering, also examining technological limitations and the impact of user language. 
Methods: the evolution of large language models, from recurrent neural networks (RNN) to the introduction of the Transformer architecture in 2017, is explained. Responses from ChatGPT 3.5 and 4.0 were evaluated in two case studies to analyze the complexity and personalization of the prompts. 
Results: in the case studies, it was found that adding context and specificity improved the models' responses. Detailed and personalized responses resulted in greater accuracy and relevance. Conclusion: the quality of LLM responses depends on the precision and specificity of the prompts. Personalization and appropriate technical language enhance interaction with Artificial Intelligence (AI), increasing user satisfaction. Future studies should analyze semantic fields and metrics to evaluate the quality of AI-generated responses.

References

1. Giray L. Prompt Engineering with ChatGPT: A Guide for Academic Writers. Ann Biomed Eng [Internet]. 2023 Dec 7;51(12):2629–33. Available from: https://link.springer.com/10.1007/s10439-023-03272-4

2. Korzynski P, Mazurek G, Krzypkowska P, Kurasinski A. Artificial intelligence prompt engineering as a new digital competence: Analysis of generative AI technologies such as ChatGPT. Entrepreneurial Business and Economics Review [Internet]. 2023 Sep 1;11(3):25–37. Available from: https://eber.uek.krakow.pl/index.php/eber/article/view/2142

3. Bouschery SG, Blazevic V, Piller FT. Augmenting human innovation teams with artificial intelligence: Exploring transformer‐based language models. Journal of Product Innovation Management [Internet]. 2023 Mar 20;40(2):139–53. Available from: https://onlinelibrary.wiley.com/doi/10.1111/jpim.12656

4. Lee U, Jung H, Jeon Y, Sohn Y, Hwang W, Moon J, et al. Few-shot is enough: exploring ChatGPT prompt engineering method for automatic question generation in english education. Educ Inf Technol (Dordr) [Internet]. 2023 Oct 31; Available from: https://link.springer.com/10.1007/s10639-023-12249-8

5. Atkinson-Abutridy J. Text Analytics [Internet]. Boca Raton: Chapman and Hall/CRC; 2022. Available from: https://www.taylorfrancis.com/books/9781003280996

6. Fuentealba D, Lopez M, Ponce HH, López M, Ponce HH, Lopez M, et al. Effects on Time and Quality of Short Text Clustering during Real-Time Presentations. IEEE Latin America Transactions [Internet]. 2021 Aug 1 [cited 2022 Mar 6];19(8):1391–9. Available from: https://ieeexplore.ieee.org/document/9475870/

7. Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, et al. Attention Is All You Need. 2017 Jun 12; Available from: http://arxiv.org/abs/1706.03762

8. Kublik S, Saboo S. Gpt-3 : The Ultimate Guide to Building NLP Products with OpenAI API.

9. Rothman D, Gulli A. Transformers for natural language processing : build, train, and fine-tuning deep neural network architectures for NLP with Python, PyTorch, TensorFlow, BERT, and GPT-3. 564 p.

10. Lim S, Schmälzle R. Artificial intelligence for health message generation: an empirical study using a large language model (LLM) and prompt engineering. Front Commun (Lausanne). 2023;8.

11. Meskó B. Prompt Engineering as an Important Emerging Skill for Medical Professionals: Tutorial. J Med Internet Res. 2023 Jan 1;25(1).

12. Shin E, Ramanathan M. Evaluation of prompt engineering strategies for pharmacokinetic data analysis with the ChatGPT large language model. J Pharmacokinet Pharmacodyn. 2023;

13. Liu K, Li W. Organisational Semiotics for Business Informatics [Internet]. London and New York: Routledge; 2014 [cited 2015 May 17]. 288 p. Available from: https://www.taylorfrancis.com/books/9780203550977

Downloads

Published

2024-09-03

How to Cite

1.
Fuentealba Cid D, Flores-Fernández C, Aguilera Eguía R. The art of prompts’ formulation: limitations, potential, and practical examples in large language models. Salud, Ciencia y Tecnología [Internet]. 2024 Sep. 3 [cited 2024 Oct. 14];4:.969. Available from: https://sct.ageditor.ar/index.php/sct/article/view/969