While fusing language models (LMs) and knowledge graphs (KGs) has become
common in commonsense question answering research, enabling faithful
chain-of-thought explanations in these models remains an open problem. One
major weakness of current KG-based explanation techniques is that they overlook
the faithfulness of generated explanations during evaluation. To address this
gap, we make two main contributions: (1) We propose and validate two
quantitative metrics - graph consistency and graph fidelity - to measure the
faithfulness of KG-based explanations. (2) We introduce Consistent GNN (CGNN),
a novel training method that adds a consistency regularization term to improve
explanation faithfulness. Our analysis shows that predictions from KG often
diverge from original model predictions. The proposed CGNN approach boosts
consistency and fidelity, demonstrating its potential for producing more
faithful explanations. Our work emphasises the importance of explicitly
evaluating suggest a path forward for developing architectures for faithful
graph-based explanations.

融合语言模型和知识图谱已经变成通识问题回答研究中的常见做法，但在这些模型中实现忠实的思维链解释仍然是一个开放问题。本研究的两个主要贡献是：(1) 提出并验证了两个定量指标 - 图一致性和图忠实度 - 用于衡量基于知识图谱的解释的忠实性。(2) 引入了一种新颖的训练方法 Consistent GNN (CGNN)，通过增加一项一致性正则化项来提高解释的忠实性。分析结果表明，知识图谱的预测往往与原始模型的预测偏离。所提出的 CGNN 方法提高了一致性和忠实度，展示了它产生更忠实解释的潜力。我们的工作强调明确评估的重要性，并为开发基于图的忠实解释结构提供了前进的方向。