Instances Need More Care: Rewriting Prompts for Instances with LLMs in the Loop Yields Better Zero-Shot Performance

arXiv:2310.02107v3 Announce Type: replace
Abstract: Large language models (LLMs) have revolutionized zero-shot task performance, mitigating the need for task-specific annotations while enhancing task generalizability. Despite its advancements, current methods using trigger phrases such as ``Let's think step by step'' remain limited. This study introduces PRomPTed, an approach that optimizes the zero-shot prompts for individual task instances following an innovative manner of ``LLMs in the loop''. Our comprehensive evaluation across 13 datasets and 10 task types based on GPT-4 reveals that …

abstract annotations arxiv cs.cl current instances language language models large language large language models llms loop performance prompts study think type zero-shot