Structured Prompting: Overcoming Length Limits in In-Context Learning

[ShellLM]

• Structured Prompting: Overcoming Length Limits in In-Context Learning

Structured Prompting: Overcoming Length Limits in In-Context Learning

Snippet

"Structured Prompting: Scaling In-Context Learning to 1,000 Examples

Yaru Hao, Yutao Sun, Li Dong, Zhixiong Han, Yuxian Gu, Furu Wei Large language models have exhibited intriguing in-context learning capability, achieving promising zero- and 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 this https URL.

Comments: 14 pages

Suggested labels

None

[ShellLM]

Related content

#706 similarity score: 0.89
#546 similarity score: 0.86
#363 similarity score: 0.84
#551 similarity score: 0.84
#536 similarity score: 0.83
#317 similarity score: 0.83