Prompt Programming
Prompt programming is the emerging practice of crafting and optimizing prompts to effectively control and utilize large language models (LLMs) for various tasks, ranging from code generation to data annotation and even operating system interaction. Current research focuses on understanding the unique challenges of prompt development, including the creation of specialized programming languages and tools for prompt optimization and debugging, as well as mitigating security risks and biases inherent in both prompts and the models themselves. This field is significant because it bridges the gap between traditional software engineering and AI, impacting software development methodologies, AI safety, and the design of more robust and ethical AI systems.
Papers
Symbolic Prompt Program Search: A Structure-Aware Approach to Efficient Compile-Time Prompt Optimization
Tobias Schnabel, Jennifer Neville
Dissecting Paraphrases: The Impact of Prompt Syntax and supplementary Information on Knowledge Retrieval from Pretrained Language Models
Stephan Linzbach, Dimitar Dimitrov, Laura Kallmeyer, Kilian Evang, Hajira Jabeen, Stefan Dietze