IFDNS: 一种迭代反馈驱动的神经符号方法用于忠实的逻辑推理
IFDNS: An Iterative Feedback-Driven Neuro-Symbolic Method for Faithful Logical Reasoning
AI总结：
IFDNS通过迭代反馈机制提升LLM逻辑推理的忠实性，有效缓解信息丢失问题，显著提高CoT和CoT-SC的性能。
摘要：
大型语言模型（LLMs）在广泛推理任务中展示了令人印象深刻的能力，包括逻辑和数学问题解决。尽管基于提示的方法如思维链（CoT）可以在一定程度上增强LLM的推理能力，但它们往往缺乏忠实性，其中得出的结论可能不与生成的推理链一致。为了解决这个问题，研究者探索了神经符号方法来增强LLM的逻辑推理能力。然而，现有的神经符号方法在处理过程中仍然面临信息丢失的挑战。为克服这些限制，我们引入了迭代反馈驱动的神经符号（IFDNS），一种新的基于提示的方法，它利用多轮反馈机制来解决LLM在处理复杂逻辑关系时的局限性。IFDNS在逻辑提取阶段利用迭代反馈来准确提取因果关系陈述，并将其转换为命题和逻辑蕴含表达式，有效缓解了信息丢失问题。此外，IFDNS与现有提示方法正交，允许无缝集成各种提示方法。在六个数据集上的实证评估表明，IFDNS在显著提高CoT和具有自我一致性（CoT-SC）的思维链性能方面表现出色。具体而言，IFDNS在LogiQA数据集上实现了CoT的+9.40%准确率提升，在PrOntoQA数据集上实现了CoT-SC的+11.70%改进。
英文摘要：
Large language models (LLMs) have demonstrated impressive capabilities across a wide range of reasoning tasks, including logical and mathematical problem-solving. While prompt-based methods like Chain-of-Thought (CoT) can enhance LLM reasoning abilities to some extent, they often suffer from a lack of faithfulness, where the derived conclusions may not align with the generated reasoning chain. To address this issue, researchers have explored neuro-symbolic approaches to bolster LLM logical reasoning capabilities. However, existing neuro-symbolic methods still face challenges with information loss during the process. To overcome these limitations, we introduce Iterative Feedback-Driven Neuro-Symbolic (IFDNS), a novel prompt-based method that employs a multi-round feedback mechanism to address LLM limitations in handling complex logical relationships. IFDNS utilizes iterative feedback during the logic extraction phase to accurately extract causal relationship statements and translate them into propositional and logical implication expressions, effectively mitigating information loss issues. Furthermore, IFDNS is orthogonal to existing prompt methods, allowing for seamless integration with various prompting approaches. Empirical evaluations across six datasets demonstrate the effectiveness of IFDNS in significantly improving the performance of CoT and Chain-of-Thought with Self-Consistency (CoT-SC). Specifically, IFDNS achieves a +9.40% accuracy boost for CoT on the LogiQA dataset and a +11.70% improvement for CoT-SC on the PrOntoQA dataset.
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。
