Though prompting LLMs with various reasoning structures produces reasoning proofs along with answers, these proofs are not ensured to be causal and reliable due to the inherent defects of LLMs. Tracking such deficiencies, we present a neuro-symbolic integration method, in which a neural LLM is used to represent the knowledge of the problem while an LLM-free symbolic solver is adopted to do deliberative reasoning using the knowledge. Specifically, our customized meta-interpreters allow the production of reasoning proofs and support flexible search strategies. These reasoning proofs are ensured to be causal and reliable because of the deterministic executing nature of the symbolic solvers. Empirically, on ProofWriter, our method surpasses the CoT baseline by nearly double in accuracy and more than triple in proof similarity. On GSM8K, our method also shows accuracy improvements and nearly doubled proof similarity. Our code is released at https://github.com/DAMO-NLP-SG/CaRing

翻译：尽管使用各种推理结构提示大语言模型能够生成推理证明与答案，但由于大语言模型固有的缺陷，这些证明无法保证具有因果性和可靠性。针对此问题，我们提出一种神经符号融合方法：使用神经大语言模型表示问题知识，同时采用无大语言模型的符号求解器基于该知识进行审慎推理。具体而言，我们定制的元解释器不仅能够生成推理证明，还支持灵活的搜索策略。由于符号求解器具有确定性执行特性，这些推理证明可确保因果性与可靠性。实验表明，在ProofWriter数据集上，我们的方法相比CoT基线准确率提升近一倍，证明相似度提升超过两倍；在GSM8K数据集上，该方法同样实现准确率提升，且证明相似度提升近一倍。我们的代码已开源至 https://github.com/DAMO-NLP-SG/CaRing。