# Learning Credible Models

arXiv: https://arxiv.org/abs/1711.03190 · HTML: https://mlsanity.com/paper/1711.03190/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Nov 2017.

## Built on by (most cited first, 8 of 8)

- [Interpretable Machine Learning: Fundamental Principles and 10 Grand Challenges](https://mlsanity.com/paper/2103.11251/) (2021)
- [Preferential Mixture-of-Experts: Interpretable Models that Rely on Human Expertise as much as Possible](https://mlsanity.com/paper/2101.05360/) (2021)
- [Dissonance Between Human and Machine Understanding](https://mlsanity.com/paper/2101.07337/) (2021)
- [Leveraging Expert Consistency to Improve Algorithmic Decision Support](https://mlsanity.com/paper/2101.09648/) (2021)
- [Hierarchical Semantic Tree Concept Whitening for Interpretable Image Classification](https://mlsanity.com/paper/2307.04343/) (2023)
- [Objective discovery of dominant dynamical processes with intelligible machine learning](https://mlsanity.com/paper/2106.12963/) (2021)
- [A Field Guide to Scientific XAI: Transparent and Interpretable Deep Learning for Bioinformatics Research](https://mlsanity.com/paper/2110.08253/) (2021)
- [Additive regularization schedule for neural architecture search](https://mlsanity.com/paper/2406.12992/) (2024)

## Abstract (arXiv)

In many settings, it is important that a model be capable of providing reasons for its predictions (i.e., the model must be interpretable). However, the model's reasoning may not conform with well-established knowledge. In such cases, while interpretable, the model lacks textitcredibility. In this work, we formally define credibility in the linear setting and focus on techniques for learning models that are both accurate and credible. In particular, we propose a regularization penalty, expert yielded estimates (EYE), that incorporates expert knowledge about well-known relationships among covariates and the outcome of interest. We give both theoretical and empirical results comparing our proposed method to several other regularization techniques. Across a range of settings, experiments on both synthetic and real data show that models learned using the EYE penalty are significantly more credible than those learned using other penalties. Applied to a large-scale patient risk stratification task, our proposed technique results in a model whose top features overlap significantly with known clinical risk factors, while still achieving good predictive performance.