元启发：利用任务无关的支架增强语言模型

Meta-Prompting: Enhancing Language Models with Task-Agnostic Scaffolding

January 23, 2024

作者: Mirac Suzgun, Adam Tauman Kalai

cs.AI

摘要

我们介绍了元提示（meta-prompting），这是一种旨在增强语言模型（LMs）功能的有效搭建技术。这种方法将单个LM转变为一个多面手指挥者，擅长管理和整合多个独立的LM查询。通过采用高级指令，元提示引导LM将复杂任务分解为更小、更易管理的子任务。然后，这些子任务由同一LM的不同“专家”实例处理，每个实例都根据特定的定制指令运行。这个过程的核心是LM本身，作为指挥者，它确保与这些专家模型的输出之间的无缝沟通和有效整合。此外，它还利用其固有的批判性思维和强大的验证过程来完善和验证最终结果。这种协作提示方法使单个LM能够同时充当全面的指挥者和一组不同专家，显著提升其在各种任务中的性能。元提示的零射击、任务不可知的特性极大地简化了用户交互，消除了对详细的任务特定指令的需求。此外，我们的研究展示了外部工具（如Python解释器）与元提示框架的无缝整合，从而扩大了其适用性和实用性。通过对GPT-4的严格实验，我们证明了元提示相对于传统的搭建方法的优越性：在包括24点游戏、一步将军和Python编程难题在内的所有任务中，元提示搭配Python解释器功能的表现超过标准提示17.1％，超过专家（动态）提示17.3％，超过多人格提示15.2％。

English

We introduce meta-prompting, an effective scaffolding technique designed to enhance the functionality of language models (LMs). This approach transforms a single LM into a multi-faceted conductor, adept at managing and integrating multiple independent LM queries. By employing high-level instructions, meta-prompting guides the LM to break down complex tasks into smaller, more manageable subtasks. These subtasks are then handled by distinct "expert" instances of the same LM, each operating under specific, tailored instructions. Central to this process is the LM itself, in its role as the conductor, which ensures seamless communication and effective integration of the outputs from these expert models. It additionally employs its inherent critical thinking and robust verification processes to refine and authenticate the end result. This collaborative prompting approach empowers a single LM to simultaneously act as a comprehensive orchestrator and a panel of diverse experts, significantly enhancing its performance across a wide array of tasks. The zero-shot, task-agnostic nature of meta-prompting greatly simplifies user interaction by obviating the need for detailed, task-specific instructions. Furthermore, our research demonstrates the seamless integration of external tools, such as a Python interpreter, into the meta-prompting framework, thereby broadening its applicability and utility. Through rigorous experimentation with GPT-4, we establish the superiority of meta-prompting over conventional scaffolding methods: When averaged across all tasks, including the Game of 24, Checkmate-in-One, and Python Programming Puzzles, meta-prompting, augmented with a Python interpreter functionality, surpasses standard prompting by 17.1%, expert (dynamic) prompting by 17.3%, and multipersona prompting by 15.2%.