Neural-symbolic methods have demonstrated efficiency in enhancing the reasoning abilities of large language models (LLMs). However, existing methods mainly rely on syntactically mapping natural languages to complete formal languages like Python and SQL. Those methods require that reasoning tasks be convertible into programs, which cater to the computer execution mindset and deviate from human reasoning habits. To broaden symbolic methods' applicability and adaptability in the real world, we propose the Meta-Reasoning from a linguistic perspective. This method empowers LLMs to deconstruct reasoning-independent semantic information into generic symbolic representations, thereby efficiently capturing more generalized reasoning knowledge. We conduct extensive experiments on more than ten datasets encompassing conventional reasoning tasks like arithmetic, symbolic, and logical reasoning, and the more complex interactive reasoning tasks like theory-of-mind reasoning. Experimental results demonstrate that Meta-Reasoning significantly enhances in-context reasoning accuracy, learning efficiency, out-of-domain generalization, and output stability compared to the Chain-of-Thought technique. Code and data are publicly available at \url{https://github.com/Alsace08/Meta-Reasoning}.

翻译：神经符号方法在提升大型语言模型推理能力方面已展现出高效性。然而，现有方法主要依赖将自然语言通过语法映射为完整的程序设计语言（如Python和SQL），这要求推理任务必须能转换为程序，从而迎合计算机执行思维，偏离了人类推理习惯。为拓展符号方法在现实世界中的适用性与适应性，我们从语言学视角提出Meta-Reasoning方法。该方法赋予大型语言模型将独立于推理的语义信息解构为通用符号表征的能力，从而高效捕获更泛化的推理知识。我们在涵盖算术推理、符号推理、逻辑推理等传统推理任务及更复杂的交互式推理（如心智理论推理）的十余个数据集上开展了广泛实验。结果表明，相较链式思考技术，Meta-Reasoning显著提升了上下文推理准确率、学习效率、跨域泛化能力与输出稳定性。相关代码与数据已开源至\url{https://github.com/Alsace08/Meta-Reasoning}。