面向常识问答中深度对齐的忠实知识图谱解释
Towards Faithful Knowledge Graph Explanation Through Deep Alignment in Commonsense Question Answering
AI总结：
针对常识问答中知识图谱解释不忠实的问题，提出LM-KG保真度指标和LKDA对齐算法，在CommonsenseQA和OpenBookQA上显著提升解释保真度与模型性能。
摘要：
语言模型（LMs）与知识图谱（KGs）的融合广泛用于常识问答，但生成忠实的解释仍具挑战性。现有方法常忽视路径解码的忠实性，导致图编码器输出与模型预测之间出现分歧。我们识别出混淆效应和LM-KG错位是产生虚假解释的关键因素。为解决此问题，我们引入LM-KG保真度指标来评估知识图谱表示的可靠性，并提出LM-KG分布感知对齐（LKDA）算法以提高解释的忠实性。在没有真实标签的情况下，我们使用所提出的保真度-稀疏性权衡曲线来评估知识图谱解释。在CommonsenseQA和OpenBookQA上的实验表明，LKDA显著提升了解释保真度和模型性能，凸显了解决分布错位以实现可靠常识推理的必要性。
英文摘要：
The fusion of language models (LMs) and knowledge graphs (KGs) is widely used in commonsense question answering, but generating faithful explanations remains challenging. Current methods often overlook path decoding faithfulness, leading to divergence between graph encoder outputs and model predictions. We identify confounding effects and LM-KG misalignment as key factors causing spurious explanations. To address this, we introduce the LM-KG Fidelity metric to assess KG representation reliability and propose the LM-KG Distribution-aware Alignment (\textit{LKDA}) algorithm to improve explanation faithfulness. Without ground truth, we evaluate KG explanations using the proposed Fidelity-Sparsity Trade-off Curve. Experiments on CommonsenseQA and OpenBookQA show that LKDA significantly enhances explanation fidelity and model performance, highlighting the need to address distributional misalignment for reliable commonsense reasoning.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
