Natural Logic at the Core: Dynamic Rewards for Entailment Tree Generation

Entailment trees are essential for enhancing interpretability and transparency in tasks like question answering and natural language understanding. However, existing approaches often lack logical consistency, as they rely on static reward structures or ignore the intricate dependencies within multi-step reasoning. To address these limitations, we propose a method that integrates natural logic principles into reinforcement learning, enabling dynamic reward computation to guide entailment tree generation. Our approach ensures logical consistency across reasoning steps while improving inter-pretability and generalization. Experiments on EntailmentBank demonstrate significant improvements over state-of-the-art methods, high-lighting the effectiveness of natural logic in structured reasoning.