XMENTOR: A Rank-Aware Aggregation Approach for Human-Centered Explainable AI in Just-in-Time Software Defect Prediction

TL;DR

XMENTOR is a VS Code plugin that combines multiple explainability methods into a clear, unified view to improve trust and usability in software defect prediction models.

Contribution

It introduces a novel rank-aware aggregation approach for explanations, enhancing interpretability and user trust in human-centered AI for software debugging.

Findings

Nearly 90% of users preferred aggregated explanations.

Aggregation reduced user confusion and supported debugging tasks.

Embedding explanations into workflows improved interpretability and trust.

Abstract

Machine learning (ML)-based defect prediction models can improve software quality. However, their opaque reasoning creates an HCI challenge because developers struggle to trust models they cannot interpret. Explainable AI (XAI) methods such as LIME, SHAP, and BreakDown aim to provide transparency, but when used together, they often produce conflicting explanations that increase confusion, frustration, and cognitive load. To address this usability challenge, we introduce XMENTOR, a human-centered, rank-aware aggregation method implemented as a VS Code plugin. XMENTOR unifies multiple post-hoc explanations into a single, coherent view by applying adaptive thresholding, rank and sign agreement, and fallback strategies to preserve clarity without overwhelming users. In a user study, nearly 90% of the participants preferred aggregated explanations, citing reduced confusion and stronger support for daily tasks of debugging and review of defects. Our findings show how combining explanations and embedding them into developer workflows can enhance interpretability, usability, and trust.