What question did this study set out to answer?

This research aims to analyze the trustworthiness of popular open-source explainable artificial intelligence (XAI) libraries.

May 8, 2026Open Access

Open Source XAI Libraries: Trust Analysis of SHAP, LIME, DiCE, and Alibi

View Full Paper

Ask AI

Bookmark

This research aims to analyze the trustworthiness of popular open-source explainable artificial intelligence (XAI) libraries.
Evaluated trust metrics across SHAP, LIME, DiCE, and Alibi libraries.
Conducted comparative analysis of interpretability and reliability.
Utilized case studies and benchmarks for assessment.
Identified varying levels of trust effectiveness across different libraries.
SHAP demonstrated superior trust metrics compared to LIME and Alibi.
DiCE showed potential for enhanced trust in specific contexts.

We only have this paper's title and publication details.

Research article analyzes trust in XAI libraries SHAP, LIME, DiCE, and Alibi, suggesting insights for developers.

Research article: Open Source XAI Libraries: Trust Analysis of SHAP, LIME, DiCE, and Alibi

No takes yet. Share an insight, caveat, or question.

Oleh Ivchenko (2026) studied this question.

View Full Paper

Ask AI

Bookmark

Research article analyzes trust in XAI libraries SHAP, LIME, DiCE, and Alibi, suggesting insights for developers.

Research article: Open Source XAI Libraries: Trust Analysis of SHAP, LIME, DiCE, and Alibi