The ability of AI systems to not only answer complex natural language questions, but also transparently justify their reasoning, is crucial for building trust and enabling effective human-AI collaboration. In domains requiring multi-hop reasoning, answers must often be constructed by combining multiple relevant sentences from a knowledge base to build an inferential path from the question toward the answer. We tackle this challenge by exploring a neuro-symbolic approach to reasoning through the generation of entailment trees – structured, step-by-step proof trees – using Large Language Models (LLMs). These trees provide interpretable justifications for the inference process. Using the EntailmentBank (CITATION) data set, we evaluated a diverse set of prompting strategies across multiple models, along with a proposal of an inference-guided prompting approach that performs well. We also fine-tuned LLMs trained specifically for proof generation by applying several data augmentation, curriculum learning, and reinforcement-guided optimization strategies. Our results show that the fine-tuned model outperforms all prompting strategies, achieving superior performance across multiple structural and semantic metrics. We also provide a detailed evaluation of which training strategies are helpful towards proof generation. Our findings highlight the importance of proof tree generation as a benchmark for evaluating structured reasoning in LLMs.

Textgraphs 2020 Workshop organized a shared task on ‘Explanation Regeneration’ that required reconstructing gold explanations for elementary science questions. This work describes our submission to the task which is based on multiple components: a BERT baseline ranking, an Integer Linear Program (ILP) based re-scoring and a regression model for re-ranking the explanation facts. Our system achieved a Mean Average Precision score of 0.3659.