Recent advancements in large language models have showcased their remarkable generalizability across various domains. However, their reasoning abilities still have significant room for improvement, especially when confronted with scenarios requiring multi-step reasoning. Although large language models possess extensive knowledge, their behavior, particularly in terms of reasoning, often fails to effectively utilize this knowledge to establish a coherent thinking paradigm. Generative language models sometimes show hallucinations as their reasoning procedures are unconstrained by logical principles. Aiming to improve the zero-shot chain-of-thought reasoning ability of large language models, we propose Logical Chain-of-Thought (LogiCoT), a neurosymbolic framework that leverages principles from symbolic logic to verify and revise the reasoning processes accordingly. Experimental evaluations conducted on language tasks in diverse domains, including arithmetic, commonsense, symbolic, causal inference, and social problems, demonstrate the efficacy of the enhanced reasoning paradigm by logic.

翻译：近期大型语言模型的进展展示了其在各个领域的显著泛化能力。然而，其推理能力仍有很大提升空间，尤其是在面对需要多步推理的场景时。尽管大型语言模型拥有广泛的知识，但其行为（特别是在推理方面）往往无法有效利用这些知识来建立连贯的思维范式。由于生成式语言模型的推理过程缺乏逻辑原则的约束，有时会出现幻觉现象。旨在提升大型语言模型的零样本思维链推理能力，我们提出了逻辑思维链（LogiCoT），这是一种神经符号框架，利用符号逻辑的原理来验证并相应修正推理过程。在包括算术、常识、符号、因果推理及社会问题等多个领域的语言任务上进行的实验评估表明，经逻辑增强的推理范式具有显著效果。