可编辑的可解释性AI:通过可编辑的可解释属性实现双向人机对齐
Editable XAI: Toward Bidirectional Human-AI Alignment with Co-Editable Explanations of Interpretable Attributes
AI总结:
本文提出可编辑的XAI方法CoExplain,通过允许用户编写规则来提升人机对齐,实验表明其在理解和控制方面优于传统只读XAI。
摘要:
虽然可解释性AI(XAI)帮助用户理解AI决策,但领域知识的不一致会导致分歧。这种不一致阻碍了理解,因为解释通常是只读的,用户缺乏改进对齐的控制。我们提出了使XAI可编辑,允许用户编写规则以提高控制并通过主动学习的生成效应获得更深入的理解。我们开发了CoExplain,利用神经网络进行通用表示和符号规则进行可解释属性的直观推理。CoExplain用忠实的代理决策树解释神经网络,将用户编写的规则解析为等价的神经网络图,并协同优化决策树。在一项用户研究(N=43)中,CoExplain和手动可编辑的XAI在理解和模型对齐方面优于只读的XAI。CoExplain使用起来更简单,编辑次数更少,时间更短。这项工作贡献了可编辑的XAI,以实现双向AI对齐,提高理解和控制。
英文摘要:
While Explainable AI (XAI) helps users understand AI decisions, misalignment in domain knowledge can lead to disagreement. This inconsistency hinders understanding, and because explanations are often read-only, users lack the control to improve alignment. We propose making XAI editable, allowing users to write rules to improve control and gain deeper understanding through the generation effect of active learning. We developed CoExplain, leveraging a neural network for universal representation and symbolic rules for intuitive reasoning on interpretable attributes. CoExplain explains the neural network with a faithful proxy decision tree, parses user-written rules as an equivalent neural network graph, and collaboratively optimizes the decision tree. In a user study (N=43), CoExplain and manually editable XAI improved user understanding and model alignment compared to read-only XAI. CoExplain was easier to use with fewer edits and less time. This work contributes Editable XAI for bidirectional AI alignment, improving understanding and control.
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。