Prompt Engineering in Large Language Models

With the undeniable rapid development of Conversational Artificial Intelligence (AI) particularly Large Language Models (LLMs), prompt engineering has become an obligatory skill for effective communication and interaction with language driven tools like ChatGPT. It can be leveraged in enforcing rules and process automation for ensuring good quality and quantity of output from LLMs. Moreover, the order of providing examples within prompts, automatic instruction generation, and selection methods has been proven to significantly impact the performance of LLMs. Prompts can be optimized to maximize a chosen score function by searching a pool of instruction candidates within LLMs. No wonder automatically generated instructions give better or similar performance than human annotated instructions and outperform baselines of LLMs, this makes prompt engineering a programming procedure for customizing outputs and interactions of LLMs. In this chapter, we provide thorough understanding of prompt engineering, latest prompt engineering techniques with relevant exercises for putting the techniques in practice. We also discuss current and future trends of LLMs and prompt engineering research, including the rise of automatic instruction generation and selection methods. These are very important for prompt and NLP engineers, conversational AI researchers, and all information seekers or users of LLMs and prompt engineering tools in sensitive domains like health care, security, education among others. The chapter provides indepth understanding of prompt engineering principles and techniques for responsible coversational AI.