Scholarlink

<p>Explainable AI technologies analyze the deep models to reveal the reasoning behind their decisions. Although recent explainable AI approaches have shown success, the question remains whether they capture both key aspects of explainability: faithfulness and alignment of explanations with human knowledge. This paper presents a framework for integrating self-explaining capabilities into a deep model to achieve high prediction performance while providing faithful and human-aligned explanations. Our framework employs interpretable features directly in the decision-making process and computes the contribution of each feature through a verification across the entire dataset. This approach excludes approximations that compromise the faithfulness and enables the model to extract human knowledge in the data. Extensive experiments demonstrate that our framework maintains 99.9% of the performance of non-explainable deep models, while achieving high precision, receiving votes as a good explanation in 89.8% of cases, and securing the highest percentage of votes for the best explanation.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Toward faithful and human-aligned self-explanation of deep models

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年9月1日

查看全文
  • Seungeon Lee,
  • Xiting Wang,
  • Ansen Zhang,
  • Sungwon Han,
  • Jing Yao,
  • Xiaoyuan Yi,
  • Xing Xie,
  • Meeyoung Cha

摘要

Explainable AI technologies analyze the deep models to reveal the reasoning behind their decisions. Although recent explainable AI approaches have shown success, the question remains whether they capture both key aspects of explainability: faithfulness and alignment of explanations with human knowledge. This paper presents a framework for integrating self-explaining capabilities into a deep model to achieve high prediction performance while providing faithful and human-aligned explanations. Our framework employs interpretable features directly in the decision-making process and computes the contribution of each feature through a verification across the entire dataset. This approach excludes approximations that compromise the faithfulness and enables the model to extract human knowledge in the data. Extensive experiments demonstrate that our framework maintains 99.9% of the performance of non-explainable deep models, while achieving high precision, receiving votes as a good explanation in 89.8% of cases, and securing the highest percentage of votes for the best explanation.