Generating coherent and credible explanations remains a significant challenge in the field of AI. In recent years, researchers have delved into the utilization of entailment trees to depict explanations, which exhibit a reasoning process of how a hypothesis is deduced from the supporting facts. However, existing models often overlook the importance of generating intermediate conclusions with logical consistency from the given facts, leading to inaccurate conclusions and undermining the overall credibility of entailment trees. To address this limitation, we propose the logical pattern memory pre-trained model (LMPM). LMPM incorporates an external memory structure to learn and store the latent representations of logical patterns, which aids in generating logically consistent conclusions. Furthermore, to mitigate the influence of logically irrelevant domain knowledge in the Wikipedia-based data, we introduce an entity abstraction approach to construct the dataset for pre-training LMPM. The experimental results highlight the effectiveness of our approach in improving the quality of entailment tree generation. By leveraging logical entailment patterns, our model produces more coherent and reasonable conclusions that closely align with the underlying premises. Code and Data are released at https://github.com/YuanLi95/T5-LMPM

翻译：生成连贯且可信的解释仍然是人工智能领域的一大挑战。近年来，研究者深入探讨如何利用蕴含树（entailment tree）来描述解释，此类树展示了从支持事实推导出假设的推理过程。然而，现有模型往往忽视了从给定事实中生成具有逻辑一致性的中间结论的重要性，导致结论不准确，削弱了蕴含树的整体可信度。为解决这一局限，我们提出逻辑模式记忆预训练模型（LMPM）。LMPM引入外部记忆结构，用于学习并存储逻辑模式的潜在表示，从而辅助生成逻辑一致的结论。此外，为减轻基于维基百科数据中逻辑无关领域知识的影响，我们引入一种实体抽象方法，用于构建LMPM预训练所需的数据集。实验结果表明，我们的方法在提升蕴含树生成质量方面具有显著效果。通过利用逻辑蕴含模式，所提模型能生成更连贯、合理的结论，使其与原始前提紧密对齐。代码与数据已发布于https://github.com/YuanLi95/T5-LMPM。