“Structured Prompting: Scaling In-Context Learning to 1,000 Examples”, 2022-12-13 ():
Large language models have exhibited intriguing in-context learning capability, achieving promising zero-shot & few-shot performance without updating the parameters. However, conventional in-context learning is usually restricted by length constraints, rendering it ineffective to absorb supervision from a large number of examples.
In order to go beyond few shots, we introduce structured prompting that breaks the length limit and scales in-context learning to thousands of examples. Specifically, demonstration examples are separately encoded with well-designed position embeddings, and then they are jointly attended by the test example using a rescaled attention mechanism. So we can scale the number of exemplars with linear complexity instead of quadratic complexity with respect to length.
Experimental results on a diverse set of tasks show that our approach improves end-task performance and reduces evaluation variance over conventional in-context learning as the number of demonstration examples increases. Code has been released at https://github.com/microsoft/LMOps/tree/main/structured_prompting/fairseq-version.