利用大语言模型开展逻辑推理中的假设演绎：一种神经符号方法
Leveraging LLMs for Hypothetical Deduction in Logical Inference: A Neuro-Symbolic Approach
AI总结：
针对大语言模型逻辑推理依赖外部符号求解器、泛化性差且易丢失信息的问题，提出神经符号方法LINA，由LLM自主完成全流程逻辑推理，采用假设演绎范式缩小搜索空间，在多项逻辑推理任务上性能显著优于现有方法。
摘要：
大语言模型（LLMs）已在包括逻辑推理在内的广泛推理任务中展现出显著潜力。尽管已有大量研究通过外部逻辑符号求解器来增强LLMs的逻辑推理能力，但两类关键挑战仍未解决：一是对不同特征的问题泛化能力较差，二是符号求解器驱动的方法不可避免地会丢失问题信息。为缓解这些问题，我们提出了LINA——一种由LLM驱动的、用于实现可信逻辑推理的神经符号方法。通过让LLM自主完成从命题逻辑提取到复杂逻辑推理的全流程转换，LINA不仅提升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有效规避了传统正向推理方法面临的搜索空间过大的难题。实验评估表明，在五项逻辑推理任务上，LINA的表现均显著优于现有命题逻辑框架和传统提示工程技术。具体而言，在FOLIO数据集上，LINA相比LINC提升了24.34%，同时相比CoT、CoT-SC等提示策略的性能提升最高达24.02%。我们的代码可在https://github.com/wufeiwuwoshihua/nshy获取。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
