Large Language Models (LLMs) have exhibited remarkable potential across a wide array of reasoning tasks, including logical reasoning. Although massive efforts have been made to empower the logical reasoning ability of LLMs via external logical symbolic solvers, crucial challenges of the poor generalization ability to questions with different features and inevitable question information loss of symbolic solver-driven approaches remain unresolved. To mitigate these issues, we introduce LINA, a LLM-driven neuro-symbolic approach for faithful logical reasoning. By enabling an LLM to autonomously perform the transition from propositional logic extraction to sophisticated logical reasoning, LINA not only bolsters the resilience of the reasoning process but also eliminates the dependency on external solvers. Additionally, through its adoption of a hypothetical-deductive reasoning paradigm, LINA effectively circumvents the expansive search space challenge that plagues traditional forward reasoning methods. Empirical evaluations demonstrate that LINA substantially outperforms both established propositional logic frameworks and conventional prompting techniques across a spectrum of five logical reasoning tasks. Specifically, LINA achieves an improvement of 24.34% over LINC on the FOLIO dataset, while also surpassing prompting strategies like CoT and CoT-SC by up to 24.02%. Our code is available at https://github.com/wufeiwuwoshihua/nshy.

翻译：大型语言模型（LLMs）在包括逻辑推理在内的广泛推理任务中展现出显著潜力。尽管已有大量研究尝试通过外部逻辑符号求解器增强LLMs的逻辑推理能力，但符号求解器驱动方法在面对不同特征问题时泛化能力不足，以及不可避免的问题信息丢失等关键挑战仍未解决。为缓解这些问题，我们提出了LINA，一种基于LLMs的神经符号方法，用于实现忠实可靠的逻辑推理。通过使LLM能够自主完成从命题逻辑提取到复杂逻辑推理的过渡，LINA不仅增强了推理过程的鲁棒性，还消除了对外部求解器的依赖。此外，通过采用假设-演绎推理范式，LINA有效规避了困扰传统前向推理方法的庞大搜索空间难题。实证评估表明，在五种逻辑推理任务中，LINA显著优于现有的命题逻辑框架和传统提示技术。具体而言，在FOLIO数据集上，LINA相比LINC实现了24.34%的性能提升，同时较CoT和CoT-SC等提示策略最高提升24.02%。我们的代码公开于https://github.com/wufeiwuwoshihua/nshy。