Comparables XAI: Faithful Example-based AI Explanations with Counterfactual Trace Adjustments

TL;DR

Comparables XAI introduces a trace adjustment method for example-based AI explanations, improving faithfulness and user understanding by systematically illustrating how feature changes influence AI decisions.

Contribution

It presents a novel trace adjustment technique for example-based explanations, enhancing interpretability and accuracy in AI decision explanations.

Findings

Trace-adjusted Comparables achieved highest faithfulness.

User accuracy improved with Trace adjustments.

Narrowest uncertainty bounds with Trace-based explanations.

Abstract

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.