Prompt Engineering: a methodology for optimizing interactions with AI-Language Models in the field of engineering

Abstract

ChatGPT is a versatile conversational Artificial Intelligence model that responds to user input prompts, with applications in academia and various sectors. However, crafting effective prompts can be challenging, leading to potentially inaccurate or contextually inappropriate responses, emphasizing the importance of prompt engineering in achieving accurate outcomes across different domains. This study aims to address this void by introducing a methodology for optimizing interactions with Artificial Intelligence language models, like ChatGPT, through prompts in the field of engineering. The approach is called GPEI and relies on the latest advancements in this area; and consists of four steps: define the objective, design the prompt, evaluate the response, and iterate. Our proposal involves two key aspects: data inclusion in prompt design for engineering applications and the integration of Explainable Artificial Intelligence principles to assess responses, enhancing transparency. It combines insights from various methodologies to address issues like hallucinations, emphasizing iterative prompt refinement techniques like posing opposing questions and using specific patterns for improvement. This methodology could improve prompt precision and utility in engineering.

Generative AI and simulation modeling: how should you (not) use large language models like ChatGPT

“…This iterative process, often involving two to three cycles per query, was crucial to ensure that each response from ChatGPT was not only relevant but also informative. While our method did not follow a formal evaluation against predetermined criteria, the overall feedback-based refinement aligns with existing research for prompt design (Vel asquez-Henao et al, 2023;White et al, 2023b). We provide an example of this iterative approach in Appendix S5 in the online supporting information.…”

Tell Me Your Prompts and I Will Make Them True: The Alchemy of Prompt Engineering and Generative AI

“…Eventually, a well-crafted prompt serves to enhance the capabilities of generative AI, allowing for more meaningful and contextually relevant outcomes." (Bozkurt & Sharma, 2023, p. 4) The effectiveness of generative AI models significantly depends on the algorithms and training data they are built upon, as well as the quality of the prompts they receive (Bsharat et al, 2023;Chen et al, 2023;Kakun & Tytenko, 2023;Liu et al, 2023a;Lo, 2023a;Lo, 2023b;O'Connor et al, 2024;Velásquez-Henao et al, 2023;White et al, 2023). Moreover, well-crafted prompts play a pivotal role in minimizing the occurrence of misleading or inaccurate outputs, often referred to as hallucinations, in generative AI models (Johnson, 2023).…”