Meta Prompting for AI Systems
arxiv(2023)
摘要
In this work, we present a comprehensive study of Meta Prompting (MP), an
innovative technique reshaping the utilization of language models (LMs) and AI
systems in problem-solving and data interaction. Grounded in type theory and
category theory, Meta Prompting emphasizes the structure and syntax of
information over traditional content-centric methods. The paper explores the
formal definitions of Meta Prompting, sets it apart from few-shot prompting,
and underlines its effectiveness in various AI applications. A key focus is
applying Meta Prompting for complex reasoning tasks, showing how it effectively
deconstructs intricate problems into simpler sub-problems, enhancing token
efficiency, and enabling more equitable problem-solving comparisons, especially
against few-shot prompting methods. Additionally, the paper introduces Meta
Prompting for prompting tasks, allowing LLMs to self-generate new prompts in a
recursive, metaprogramming-like manner. Empirical experiments, including using
a Qwen-72B base language model equipped with meta prompt without
instruction-tuning to solve MATH problems with accuracy at 46.3
the supervised fine-tuned counterpart trained with extensive mathematical QA
instruction pairs and even the initial version of GPT-4, solving GSM8K problems
with 83.5
and solving the Game of 24 tasks with a 100
demonstrate the meta prompting's efficacy in achieving high accuracy and
efficiency, showcasing Meta Prompting's transformative impact on AI
problem-solving. The code is available at
https://github.com/meta-prompting/meta-prompting.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要