Our method for selecting prompt templates maximizes mutual information between input and model output, improving prompt accuracy without needing ground truth labels.

An Information-theoretic Approach to Prompt Engineering Without Ground Truth Labels

Prompt engineering is an emerging skill for medical professionals to improve their interactions with large language models (LLMs) in AI-based tools, enhancing their use of AI-based tools in healthcare.

Prompt Engineering as an Important Emerging Skill for Medical Professionals: Tutorial

This paper presents a catalog of prompt engineering techniques in pattern form, enabling efficient output generation and interaction with large language models like ChatGPT, enhancing software development tasks.

A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPT

Our meta-prompt, PE2, effectively guides large language models (LLMs) to perform automatic prompt engineering, improving their performance on various datasets and tasks.

Prompt Engineering a Prompt Engineer

Effective AI prompt engineering can significantly enhance the performance of large language models, generating more accurate and contextually relevant results across various domains.

Artificial intelligence prompt engineering as a new digital competence: Analysis of generative AI technologies such as ChatGPT

Prompt engineering enables the adaptation of pre-trained vision-language models to new tasks, enabling easier application in real-world tasks without updating model parameters.

A Systematic Survey of Prompt Engineering on Vision-Language Foundation Models

Model-driven engineering supports prompt engineering by creating platform-independent, adaptable prompts for generative AI systems, with tool support through a Langium-based Visual Studio Code plugin.

Model-Driven Prompt Engineering

Prompt engineering is a non-intuitive creative skill that requires practice and learning before it can be used effectively for creating AI art with text-to-image generation.

Prompting AI Art: An Investigation into the Creative Skill of Prompt Engineering

Automatic Prompt Engineer (APE) effectively generates and selects natural language instructions for large language models, outperforming previous methods and human-level prompts on 19/24 tasks.

Large Language Models Are Human-Level Prompt Engineers

Prompt engineering optimizes Large Language Models (LLMs) by structuring input text, with external assistance and plugins, and has transformative potential in fields like education and programming.

Unleashing the potential of prompt engineering in Large Language Models: a comprehensive review

Declarative prompt engineering, leveraging declarative crowdsourcing ideas, can optimize quality and cost in LLM-powered data processing workflows.

Revisiting Prompt Engineering via Declarative Crowdsourcing

Prompt-engineering, a combination of AI, linguistics, and user experience design, can optimize output quality in reference services, offering opportunities for growth for library professionals.

The Art and Science of Prompt Engineering: A New Literacy in the Information Age

A greedy approach with beam search and novel techniques using search history improves automatic long prompt engineering, achieving an average of 9.2% accuracy gain on Big Bench Hard tasks.

Automatic Engineering of Long Prompts

Prompt engineering is crucial for effectively communicating with generative language models in medical education, addressing concerns like accuracy, bias, privacy, and excessive reliance on technology.

Prompt Engineering in Medical Education

Prompt engineering can revolutionize medical education by improving understanding and deepening understanding in diverse fields like anatomy, physiology, pathology, pharmacology, and clinical skills.

Prompt Engineering For Students of Medicine and Their Teachers

Prompt engineering using existing conversation threads may be a competitive alternative to supervised methods for contextual stance classification, with potential improvements in accuracy and development costs.

Contextual stance classification using prompt engineering

Prompt engineering has significantly contributed to healthcare NLP applications like question-answering systems, text summarization, and machine translation, with its importance increasing with improved language models.

Prompt Engineering for Healthcare: Methodologies and Applications

Prompt engineering librarians could bridge the gap in AI literacy and enhance interactions with AI systems, contributing to AI accessibility and understanding.

The prompt engineering librarian

Synthetic text images are effective visual prompts for vision-language models, improving few-shot learning, base-to-new generalization, and domain generalization.

LoGoPrompt: Synthetic Text Images Can Be Good Visual Prompts for Vision-Language Models

Prompt engineers and librarians can work together, but both need to recognize the distinct nature of AI models and traditional literature databases for efficient work efficiency.

Prompt Engineers or Librarians? An Exploration

These studies suggest that prompt engineering enhances the performance and adaptability of large language models across various domains, including healthcare, software development, and AI art, by optimizing input structuring and utilizing tools and techniques for improved output generation.