Feature-Guided Neighbor Selection for Non-Expert Evaluation of Model Predictions
This addresses the challenge of making AI model predictions more interpretable for users without domain expertise, representing an incremental improvement in post hoc explanation methods.
The paper tackled the problem of unclear interpretable outputs for non-expert users in Explainable AI by introducing Feature-Guided Neighbor Selection (FGNS), which improved non-experts' ability to identify model errors in a user study with 98 participants, showing faster and more accurate decisions compared to traditional k-NN explanations.
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.