Explabox: A Python Toolkit for Standardized Auditing and Explanation of Text Models
Open Access
- 13 October 2025
- journal article
- Published by The Open Journal in Journal of Open Source Software
- Vol. 10 (114) , 8253
Abstract
Developed to meet the practical machine learning (ML) auditing requirements of the Netherlands National Police, Explabox is an open-source Python toolkit that implements a standardized four-step analysis workflow: explore, examine, explain, and expose. The framework transforms models and data (ingestibles) into interpretable reports and visualizations (digestibles), covering everything from data statistics and performance metrics to local and global explanations, and sensitivity testing for fairness, robustness, and security. Designed for developers, testers, and auditors, Explabox operationalizes the entire audit lifecycle in a reproducible manner. The initial release is focused on text classification and regression models, with plans for future expansion.Keywords
This publication has 11 references indexed in Scilit:
- A Survey on Bias and Fairness in Machine LearningACM Computing Surveys, 2021
- imodels: a python package for fitting interpretable modelsJournal of Open Source Software, 2021
- Explanatory Model Analysis2021
- Beyond Accuracy: Behavioral Testing of NLP Models with CheckList2020
- One Explanation Does Not Fit All: A Toolkit and Taxonomy of AI Explainability TechniquesarXiv, 2019
- AI Fairness 360: An Extensible Toolkit for Detecting, Understanding, and Mitigating Unwanted Algorithmic BiasarXiv, 2018
- Local Rule-Based Explanations of Black Box Decision SystemsarXiv, 2018
- Anchors: High-Precision Model-Agnostic ExplanationsProceedings of the AAAI Conference on Artificial Intelligence, 2018
- Interacting with Predictions2016
- “Why Should I Trust You?”: Explaining the Predictions of Any Classifier2016