Prompt Engineering
Prompt engineering is the art and science of crafting effective instructions—prompts—to guide large language models (LLMs) towards desired outputs. Current research focuses on developing automated methods for prompt optimization, exploring techniques like chain-of-thought prompting, and adapting prompts to specific LLMs and tasks (e.g., code generation, question answering, medical image analysis). This field is significant because effective prompt engineering dramatically improves the accuracy, efficiency, and reliability of LLMs across diverse applications, ranging from healthcare and education to software development and scientific research.
Papers
What's the Magic Word? A Control Theory of LLM Prompting
Aman Bhargava, Cameron Witkowski, Manav Shah, Matt Thomson
Co-audit: tools to help humans double-check AI-generated content
Andrew D. Gordon, Carina Negreanu, José Cambronero, Rasika Chakravarthy, Ian Drosos, Hao Fang, Bhaskar Mitra, Hannah Richardson, Advait Sarkar, Stephanie Simmons, Jack Williams, Ben Zorn
SPELL: Semantic Prompt Evolution based on a LLM
Yujian Betterest Li, Kai Wu
PEACE: Prompt Engineering Automation for CLIPSeg Enhancement in Aerial Robotics
Haechan Mark Bong, Rongge Zhang, Antoine Robillard, Ricardo de Azambuja, Giovanni Beltrame
Batch Calibration: Rethinking Calibration for In-Context Learning and Prompt Engineering
Han Zhou, Xingchen Wan, Lev Proleev, Diana Mincu, Jilin Chen, Katherine Heller, Subhrajit Roy