We study a synthetic corpus-based approach for language models (LMs) to acquire logical deductive reasoning ability. The previous studies generated deduction examples using specific sets of deduction rules. However, these rules were limited or otherwise arbitrary. This can limit the generalizability of acquired deductive reasoning ability. We rethink this and adopt a well-grounded set of deduction rules based on formal logic theory, which can derive any other deduction rules when combined in a multistep way. We empirically verify that LMs trained on the proposed corpora, which we name $\textbf{FLD}$ ($\textbf{F}$ormal $\textbf{L}$ogic $\textbf{D}$eduction), acquire more generalizable deductive reasoning ability. Furthermore, we identify the aspects of deductive reasoning ability on which deduction corpora can enhance LMs and those on which they cannot. Finally, on the basis of these results, we discuss the future directions for applying deduction corpora or other approaches for each aspect. We release the code, data, and models.

翻译：我们研究了一种基于合成语料库的方法，使语言模型（LMs）获得逻辑演绎推理能力。先前的研究使用特定的演绎规则集生成推理示例。然而，这些规则要么有限，要么随意。这可能会限制所获得演绎推理能力的泛化性。我们对此进行反思，并采用基于形式逻辑理论的严谨演绎规则集，这些规则通过多步组合可以推导出任何其他演绎规则。我们通过实验验证，在所提出的语料库（命名为$\textbf{FLD}$，即$\textbf{F}$ormal $\textbf{L}$ogic $\textbf{D}$eduction）上训练的语言模型获得了更可泛化的演绎推理能力。此外，我们识别了演绎推理能力中演绎语料库能够增强的方面以及无法增强的方面。最后，基于这些结果，我们讨论了针对每个方面应用演绎语料库或其他方法的未来方向。我们公开了代码、数据和模型。