用可比案例加反事实追踪，让AI解释更可信、易懂。
Comparables XAI: Faithful Example-based AI Explanations with Counterfactual Trace Adjustments
- 基于可比案例，逐属性追踪反事实变化路径
- 相比线性调整或未调整案例，解释精度与用户理解度提升显著
- 适合需要高可信度解释的金融、房产等决策场景
以实例解释AI决策是一种直观方式，但当实例间特征差异大时，难以判断决策值应如何变化。我们借鉴房地产估价中的可比案例（Comparables）方法：通过假设调整每个可比案例的属性，并根据影响因素相应改变估值。本文提出Comparables XAI，利用痕迹调整（Trace adjustment）技术，从每个可比案例到目标案例（Subject），逐个属性单调追踪反事实变化路径，构建可解释性框架。在模型评估和用户研究中，轨迹调整后的可比案例在解释忠实度、精确度、用户准确率及不确定性区间方面均优于线性回归、线性调整可比案例或未调整案例。本研究为基于实例的解释提供了新的分析基础，提升了用户对AI决策的理解能力。
原文摘要 · Abstract (English)
Explaining with examples is an intuitive way to justify AI decisions. However, it is challenging to understand how a decision value should change relative to the examples with many features differing by large amounts. We draw from real estate valuation that uses Comparables-examples with known values for comparison. Estimates are made more accurate by hypothetically adjusting the attributes of each Comparable and correspondingly changing the value based on factors. We propose Comparables XAI for relatable example-based explanations of AI with Trace adjustments that trace counterfactual changes from each Comparable to the Subject, one attribute at a time, monotonically along the AI feature space. In modelling and user studies, Trace-adjusted Comparables achieved the highest XAI faithfulness and precision, user accuracy, and narrowest uncertainty bounds compared to linear regression, linearly adjusted Comparables, or unadjusted Comparables. This work contributes a new analytical basis for using example-based explanations to improve user understanding of AI decisions.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。