# Counterfactual Reasoning for Bias Evaluation and Detection in a Fairness under Unawareness setting

arXiv: https://arxiv.org/abs/2302.08204 · HTML: https://mlsanity.com/paper/2302.08204/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 55 references that are in the map.
- First posted on arXiv 16 Feb 2023.

## Builds on (most cited first, 16 of 16)

- [Equality of Opportunity in Supervised Learning](https://mlsanity.com/paper/1610.02413/) (2016)
- [A Survey on Bias and Fairness in Machine Learning](https://mlsanity.com/paper/1908.09635/) (2019)
- [Explanation in Artificial Intelligence: Insights from the Social Sciences](https://mlsanity.com/paper/1706.07269/) (2017)
- [Counterfactual Fairness](https://mlsanity.com/paper/1703.06856/) (2017)
- [Mitigating Unwanted Biases with Adversarial Learning](https://mlsanity.com/paper/1801.07593/) (2018)
- [Explaining Machine Learning Classifiers through Diverse Counterfactual Explanations](https://mlsanity.com/paper/1905.07697/) (2019)
- [Algorithmic decision making and the cost of fairness](https://mlsanity.com/paper/1701.08230/) (2017)
- [Empirical Risk Minimization under Fairness Constraints](https://mlsanity.com/paper/1802.08626/) (2018)
- [Model-Agnostic Counterfactual Explanations for Consequential Decisions](https://mlsanity.com/paper/1905.11190/) (2019)
- [Fairness Under Unawareness: Assessing Disparity When Protected Class Is Unobserved](https://mlsanity.com/paper/1811.11154/) (2018)
- [Fairness in Risk Assessment Instruments: Post-Processing to Achieve Counterfactual Equalized Odds](https://mlsanity.com/paper/2009.02841/) (2020)
- [Fair Normalizing Flows](https://mlsanity.com/paper/2106.05937/) (2021)
- [Fair lending needs explainable models for responsible recommendation](https://mlsanity.com/paper/1809.04684/) (2018)
- [Measuring Fairness Under Unawareness of Sensitive Attributes: A Quantification-Based Approach](https://mlsanity.com/paper/2109.08549/) (2021)
- [Hunting for Discriminatory Proxies in Linear Regression Models](https://mlsanity.com/paper/1810.07155/) (2018)
- [Active Fairness Instead of Unawareness](https://mlsanity.com/paper/2009.06251/) (2020)

## Built on by (most cited first, 2 of 2)

- [LIBERTy: A Causal Framework for Benchmarking Concept-Based Explanations of LLMs with Structural Counterfactuals](https://mlsanity.com/paper/2601.10700/) (2026)
- [Facets of Disparate Impact: Evaluating Legally Consistent Bias in Machine Learning](https://mlsanity.com/paper/2505.05471/) (2025)

## Abstract (arXiv)

Current AI regulations require discarding sensitive features (e.g., gender, race, religion) in the algorithm's decision-making process to prevent unfair outcomes. However, even without sensitive features in the training set, algorithms can persist in discrimination. Indeed, when sensitive features are omitted (fairness under unawareness), they could be inferred through non-linear relations with the so called proxy features. In this work, we propose a way to reveal the potential hidden bias of a machine learning model that can persist even when sensitive features are discarded. This study shows that it is possible to unveil whether the black-box predictor is still biased by exploiting counterfactual reasoning. In detail, when the predictor provides a negative classification outcome, our approach first builds counterfactual examples for a discriminated user category to obtain a positive outcome. Then, the same counterfactual samples feed an external classifier (that targets a sensitive feature) that reveals whether the modifications to the user characteristics needed for a positive outcome moved the individual to the non-discriminated group. When this occurs, it could be a warning sign for discriminatory behavior in the decision process. Furthermore, we leverage the deviation of counterfactuals from the original sample to determine which features are proxies of specific sensitive information. Our experiments show that, even if the model is trained without sensitive features, it often suffers discriminatory biases.