# Making Fair ML Software using Trustworthy Explanation

arXiv: https://arxiv.org/abs/2007.02893 · HTML: https://mlsanity.com/paper/2007.02893/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Jul 2020.

## Built on by (most cited first, 24 of 24)

- [A survey on datasets for fairness-aware machine learning](https://mlsanity.com/paper/2110.00530/) (2021)
- [Bias in Machine Learning Software: Why? How? What to do?](https://mlsanity.com/paper/2105.12195/) (2021)
- [Fair Preprocessing: Towards Understanding Compositional Fairness of Data Transformers in Machine Learning Pipeline](https://mlsanity.com/paper/2106.06054/) (2021)
- [A Comprehensive Empirical Study of Bias Mitigation Methods for Machine Learning Classifiers](https://mlsanity.com/paper/2207.03277/) (2022)
- [Explanations, Fairness, and Appropriate Reliance in Human-AI Decision-Making](https://mlsanity.com/paper/2209.11812/) (2022)
- [FairMask: Better Fairness via Model-based Rebalancing of Protected Attributes](https://mlsanity.com/paper/2110.01109/) (2021)
- [A Critical Survey on Fairness Benefits of Explainable AI](https://mlsanity.com/paper/2310.13007/) (2023)
- [Fair Enough: Searching for Sufficient Measures of Fairness](https://mlsanity.com/paper/2110.13029/) (2021)
- [Explainable Artificial Intelligence (XAI) for Internet of Things: A Survey](https://mlsanity.com/paper/2206.04800/) (2022)
- [Better sampling in explanation methods can prevent dieselgate-like deception](https://mlsanity.com/paper/2101.11702/) (2021)
- [FairBalance: How to Achieve Equalized Odds With Data Pre-processing](https://mlsanity.com/paper/2107.08310/) (2021)
- [Fair-SSL: Building fair ML Software with less data](https://mlsanity.com/paper/2111.02038/) (2021)
- [Trust in AI and Implications for the AEC Research: A Literature Analysis](https://mlsanity.com/paper/2203.03847/) (2022)
- [EMaP: Explainable AI with Manifold-based Perturbations](https://mlsanity.com/paper/2209.08453/) (2022)
- [Bias Mitigation Methods for Binary Classification Decision-Making Systems: Survey and Recommendations](https://mlsanity.com/paper/2305.20020/) (2023)
- [Towards Better Fairness-Utility Trade-off: A Comprehensive Measurement-Based Reinforcement Learning Framework](https://mlsanity.com/paper/2307.11379/) (2023)
- [Identifying Reasons for Bias: An Argumentation-Based Approach](https://mlsanity.com/paper/2310.16506/) (2023)
- [Mapping the Potential of Explainable AI for Fairness Along the AI Lifecycle](https://mlsanity.com/paper/2404.18736/) (2024)
- [Unbiasing on the Fly: Explanation-Guided Human Oversight of Machine Learning System Decisions](https://mlsanity.com/paper/2406.17906/) (2024)
- [Software Engineering Principles for Fairer Systems: Experiments with GroupCART](https://mlsanity.com/paper/2504.12587/) (2025)
- [Fairer Software Made Easier (using "Keys")](https://mlsanity.com/paper/2107.05088/) (2021)
- [Contexts Matter: An Empirical Study on Contextual Influence in Fairness Testing for Deep Learning Systems](https://mlsanity.com/paper/2408.06102/) (2024)
- [Whence Is A Model Fair? Fixing Fairness Bugs via Propensity Score Matching](https://mlsanity.com/paper/2504.17066/) (2025)
- [Empowering Affected Individuals to Shape AI Fairness Assessments: Processes, Criteria, and Tools](https://mlsanity.com/paper/2602.06984/) (2026)

## Abstract (arXiv)

Machine learning software is being used in many applications (finance, hiring, admissions, criminal justice) having a huge social impact. But sometimes the behavior of this software is biased and it shows discrimination based on some sensitive attributes such as sex, race, etc. Prior works concentrated on finding and mitigating bias in ML models. A recent trend is using instance-based model-agnostic explanation methods such as LIME to find out bias in the model prediction. Our work concentrates on finding shortcomings of current bias measures and explanation methods. We show how our proposed method based on K nearest neighbors can overcome those shortcomings and find the underlying bias of black-box models. Our results are more trustworthy and helpful for the practitioners. Finally, We describe our future framework combining explanation and planning to build fair software.