arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2303.05729cs.AIcs.HCcs.LG
收藏

使用反事实解释模型置信度

Explaining Model Confidence Using Counterfactuals

School of Computing and Information Systems, The University of Melbourne(墨尔本大学计算与信息系统学院)

Thao Le, Tim Miller, Ronal Singh, Liz Sonenberg

摘要:

人类与人工智能交互的可信度得分已被证明有助于建立人类与人工智能系统之间的信任。然而,大多数现有的研究仅使用置信度得分作为一种沟通形式。由于置信度分数只是另一个模型输出,因此用户可能希望了解算法为什么有信心确定是否接受置信度分数。在本文中,我们表明,信心分数的反事实解释有助于研究参与者更好地理解和更好地信任机器学习模型的预测。我们提出了两种使用反事实解释理解模型置信度的方法:(1)基于反事实示例;(2)基于反事实空间的可视化。两者都增加了研究参与者对没有解释的基线的理解和信任,但定性结果表明,它们的使用方式完全不同,从而提出了何时使用每一种解释的建议以及设计更好解释的方向。

英文摘要:

Displaying confidence scores in human-AI interaction has been shown to help build trust between humans and AI systems. However, most existing research uses only the confidence score as a form of communication. As confidence scores are just another model output, users may want to understand why the algorithm is confident to determine whether to accept the confidence score. In this paper, we show that counterfactual explanations of confidence scores help study participants to better understand and better trust a machine learning model's prediction. We present two methods for understanding model confidence using counterfactual explanation: (1) based on counterfactual examples; and (2) based on visualisation of the counterfactual space. Both increase understanding and trust for study participants over a baseline of no explanation, but qualitative results show that they are used quite differently, leading to recommendations of when to use each one and directions of designing better explanations.

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。

↑