研究人员推出TRUST，一个用于在高风险决策系统中生成目标置信度反事实解释的新颖框架。与关注最小输入更改的现有方法不同，TRUST允许用户指定期望的预测置信度水平。这种方法通过直接搜索满足置信度目标的最小修改，而不是在生成后评估置信度，从而实现更强大、更可解释的算法追索形式。该框架利用概率Tsetlin机器（PTMs）和贝叶斯优化来连接预测置信度与决策规则稳定性，为算法决策的可靠性提供可操作的见解。 AI
影响 通过允许对置信度目标进行显式控制，增强了关键应用中AI决策的可解释性和鲁棒性。
排序理由 该集群包含一篇详细介绍AI解释新框架和方法的论文。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2606.18832v1 Announce Type: cross Abstract: Counterfactual explanations are widely used to provide algorithmic recourse in high-stakes decision-making systems. Most existing methods seek the smallest change to an input that flips a model's decision. However, decision-makers…
Counterfactual explanations are widely used to provide algorithmic recourse in high-stakes decision-making systems. Most existing methods seek the smallest change to an input that flips a model's decision. However, decision-makers often rely not only on predicted labels but also …