Automatic Prompt Selection for Large Language Models

arXiv:2404.02717v1 Announce Type: cross
Abstract: Large Language Models (LLMs) can perform various natural language processing tasks with suitable instruction prompts. However, designing effective prompts manually is challenging and time-consuming. Existing methods for automatic prompt optimization either lack flexibility or efficiency. In this paper, we propose an effective approach to automatically select the optimal prompt for a given input from a finite set of synthetic candidate prompts. Our approach consists of three steps: (1) clustering the training data and generating candidate …

abstract arxiv cs.cl cs.lg designing efficiency flexibility however language language models language processing large language large language models llms natural natural language natural language processing optimization paper processing prompt prompts tasks type