Lilian Weng‘s review: Prompt engineering
Large language models can be few-shot or zero-shot learners when the prompt is designed well. Can we do this systematically?
Ding2021OpenPrompt is an open-source framework for prompt learning.
How can we understand the differences between many possible prompts? Gonen2022demystifying test a hypothesis that the prompt that is familiar to the model (low Perplexity) is related to its performance.