# Biased Models Have Biased Explanations

arXiv: https://arxiv.org/abs/2012.10986 · HTML: https://mlsanity.com/paper/2012.10986/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Dec 2020.

## Built on by (most cited first, 10 of 10)

- [Impossibility Theorems for Feature Attribution](https://mlsanity.com/paper/2212.11870/) (2022)
- [RKHS-SHAP: Shapley Values for Kernel Methods](https://mlsanity.com/paper/2110.09167/) (2021)
- [A Critical Survey on Fairness Benefits of Explainable AI](https://mlsanity.com/paper/2310.13007/) (2023)
- [Bt-GAN: Generating Fair Synthetic Healthdata via Bias-transforming Generative Adversarial Networks](https://mlsanity.com/paper/2404.13634/) (2024)
- [Beyond Predictions: A Participatory Framework for Multi-Stakeholder Decision-Making](https://mlsanity.com/paper/2502.08542/) (2025)
- [Explanations as Bias Detectors: A Critical Study of Local Post-hoc XAI Methods for Fairness Exploration](https://mlsanity.com/paper/2505.00802/) (2025)
- [Fairness of Explanations in Artificial Intelligence (AI): A Unifying Framework, Axioms, and Future Direction toward Responsible AI](https://mlsanity.com/paper/2605.09852/) (2026)
- [Achieving Transparency in Distributed Machine Learning with Explainable Data Collaboration](https://mlsanity.com/paper/2212.03373/) (2022)
- [EVolutionary Independent DEtermiNistiC Explanation](https://mlsanity.com/paper/2501.16357/) (2025)
- [MUPAX: Multidimensional Problem Agnostic eXplainable AI](https://mlsanity.com/paper/2507.13090/) (2025)

## Abstract (arXiv)

We study fairness in Machine Learning (FairML) through the lens of attribute-based explanations generated for machine learning models. Our hypothesis is: Biased Models have Biased Explanations. To establish that, we first translate existing statistical notions of group fairness and define these notions in terms of explanations given by the model. Then, we propose a novel way of detecting (un)fairness for any black box model. We further look at post-processing techniques for fairness and reason how explanations can be used to make a bias mitigation technique more individually fair. We also introduce a novel post-processing mitigation technique which increases individual fairness in recourse while maintaining group level fairness.