Feature-Guided Neighbor Selection for Non-Expert Evaluation of Model Predictions

TL;DR

This paper presents FGNS, a novel method that improves interpretability for non-expert users by selecting class-representative examples based on feature importance, leading to better error detection and faster decision-making.

Contribution

The introduction of Feature-Guided Neighbor Selection (FGNS), a post hoc explanation method that enhances interpretability by incorporating feature importance for neighbor selection.

Findings

FGNS improves non-experts' ability to identify model errors.

Participants made faster, more accurate decisions with FGNS explanations.

FGNS selects neighbors reflecting class characteristics, not just feature-space proximity.

Abstract

Explainable AI (XAI) methods often struggle to generate clear, interpretable outputs for users without domain expertise. We introduce Feature-Guided Neighbor Selection (FGNS), a post hoc method that enhances interpretability by selecting class-representative examples using both local and global feature importance. In a user study (N = 98) evaluating Kannada script classifications, FGNS significantly improved non-experts' ability to identify model errors while maintaining appropriate agreement with correct predictions. Participants made faster and more accurate decisions compared to those given traditional k-NN explanations. Quantitative analysis shows that FGNS selects neighbors that better reflect class characteristics rather than merely minimizing feature-space distance, leading to more consistent selection and tighter clustering around class prototypes. These results support FGNS as a step toward more human-aligned model assessment, although further work is needed to address the gap between explanation quality and perceived trust.