Scholarlink

The lack of proper formalization in non-symbolic explainable artificial intelligence (XAI) has resulted in a growing number of provable flaws in widely adopted methods of explainability. This paper reviews some of the most visible misconceptions of non-symbolic XAI, and shows how logic-based XAI has been applied to uncover and correct those misconceptions. The paper also summarizes ongoing research to develop a sound, scalable and human-understandable framework for rigorously defined XAI.

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

Uncovering and Correcting XAI’s Misconceptions Logic to the Rescue

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Joao Marques-Silva

摘要

The lack of proper formalization in non-symbolic explainable artificial intelligence (XAI) has resulted in a growing number of provable flaws in widely adopted methods of explainability. This paper reviews some of the most visible misconceptions of non-symbolic XAI, and shows how logic-based XAI has been applied to uncover and correct those misconceptions. The paper also summarizes ongoing research to develop a sound, scalable and human-understandable framework for rigorously defined XAI.