Existing knowledge-enhanced methods have achieved remarkable results in certain QA tasks via obtaining diverse knowledge from different knowledge bases. However, limited by the properties of retrieved knowledge, they still have trouble benefiting from both the knowledge relevance and distinguishment simultaneously. To address the challenge, we propose CPACE, a Concept-centric Prompt-bAsed Contrastive Explanation Generation model, which aims to convert obtained symbolic knowledge into a contrastive explanation for better distinguishing the differences among given candidates. Firstly, following previous works, we retrieve different types of symbolic knowledge with a concept-centric knowledge extraction module. After that, we generate corresponding contrastive explanations using acquired symbolic knowledge and explanation prompts as guidance for better modeling the knowledge distinguishment and interpretability. Finally, we regard the generated contrastive explanation as external knowledge for downstream task enhancement. We conduct a series of experiments on three widely-used question-answering datasets: CSQA, QASC, and OBQA. Experimental results demonstrate that with the help of generated contrastive explanation, our CPACE model achieves new SOTA on CSQA (89.8% on the testing set, 0.9% higher than human performance), and gains impressive improvement on QASC and OBQA (4.2% and 3.5%, respectively).

翻译：现有知识增强方法通过从不同知识库获取多样化知识，已在特定问答任务中取得显著成果。然而受限于检索知识的属性，这些方法仍难以同时兼顾知识相关性与区分性。为应对这一挑战，我们提出CPACE——一种以概念为中心的基于提示的对比解释生成模型，旨在将获取的符号知识转化为对比解释，从而更好地区分候选选项之间的差异。首先，遵循先前工作，我们通过以概念为中心的知识提取模块检索不同类型的符号知识。随后，利用所获取的符号知识与解释提示作为引导，生成相应的对比解释，以增强知识区分能力与可解释性。最后，我们将生成的对比解释作为外部知识用于下游任务增强。我们在三个广泛使用的问答数据集（CSQA、QASC和OBQA）上开展系列实验。实验结果表明，借助生成的对比解释，我们的CPACE模型在CSQA上达到新SOTA（测试集准确率89.8%，比人类表现高0.9%），并在QASC和OBQA上取得显著提升（分别提升4.2%和3.5%）。