EvaluateXAI: A Framework to Evaluate the Reliability and Consistency of Rule-based XAI Techniques for Software Analytics Tasks

TL;DR

This paper introduces EvaluateXAI, a framework to assess the reliability and consistency of rule-based XAI techniques like PyExplainer and LIME in explaining ML models for software analytics, revealing significant inconsistencies.

Contribution

The paper proposes a novel evaluation framework and metrics to automatically assess rule-based XAI techniques' effectiveness in software analytics tasks, highlighting their unreliability.

Findings

XAI explanations are often inconsistent and unreliable.

None of the evaluation metrics reached 100% effectiveness.

PyExplainer and LIME failed to provide consistent explanations in most cases.

Abstract

The advancement of machine learning (ML) models has led to the development of ML-based approaches to improve numerous software engineering tasks in software maintenance and evolution. Nevertheless, research indicates that despite their potential successes, ML models may not be employed in real-world scenarios because they often remain a black box to practitioners, lacking explainability in their reasoning. Recently, various rule-based model-agnostic Explainable AI (XAI) techniques, such as PyExplainer and LIME, have been employed to explain the predictions of ML models in software analytics tasks. This paper assesses the ability of these techniques (e.g., PyExplainer and LIME) to generate reliable and consistent explanations for ML models across various software analytics tasks, including Just-in-Time (JIT) defect prediction, clone detection, and the classification of useful code review comments. Our manual investigations find inconsistencies and anomalies in the explanations generated by these techniques. Therefore, we design a novel framework: Evaluation of Explainable AI (EvaluateXAI), along with granular-level evaluation metrics, to automatically assess the effectiveness of rule-based XAI techniques in generating reliable and consistent explanations for ML models in software analytics tasks. After conducting in-depth experiments involving seven state-of-the-art ML models trained on five datasets and six evaluation metrics, we find that none of the evaluation metrics reached 100\%, indicating the unreliability of the explanations generated by XAI techniques. Additionally, PyExplainer and LIME failed to provide consistent explanations for 86.11% and 77.78% of the experimental combinations, respectively. Therefore, our experimental findings emphasize the necessity for further research in XAI to produce reliable and consistent explanations for ML models in software analytics tasks.