# Interpretable Companions for Black-Box Models

arXiv: https://arxiv.org/abs/2002.03494 · HTML: https://mlsanity.com/paper/2002.03494/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Feb 2020.

## Built on by (most cited first, 3 of 3)

- [Learning Hybrid Interpretable Models: Theory, Taxonomy, and Methods](https://mlsanity.com/paper/2303.04437/) (2023)
- [Partially Interpretable Estimators (PIE): Black-Box-Refined Interpretable Machine Learning](https://mlsanity.com/paper/2105.02410/) (2021)
- [Mixtures of Transparent Local Models](https://mlsanity.com/paper/2601.10541/) (2026)

## Abstract (arXiv)

We present an interpretable companion model for any pre-trained black-box classifiers. The idea is that for any input, a user can decide to either receive a prediction from the black-box model, with high accuracy but no explanations, or employ a companion rule to obtain an interpretable prediction with slightly lower accuracy. The companion model is trained from data and the predictions of the black-box model, with the objective combining area under the transparency--accuracy curve and model complexity. Our model provides flexible choices for practitioners who face the dilemma of choosing between always using interpretable models and always using black-box models for a predictive task, so users can, for any given input, take a step back to resort to an interpretable prediction if they find the predictive performance satisfying, or stick to the black-box model if the rules are unsatisfying. To show the value of companion models, we design a human evaluation on more than a hundred people to investigate the tolerable accuracy loss to gain interpretability for humans.