# AI Fairness: from Principles to Practice

arXiv: https://arxiv.org/abs/2207.09833 · HTML: https://mlsanity.com/paper/2207.09833/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 39 references that are in the map.
- First posted on arXiv 20 Jul 2022.

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

- [A Survey on Bias and Fairness in Machine Learning](https://mlsanity.com/paper/1908.09635/) (2019)
- [Fair prediction with disparate impact: A study of bias in recidivism prediction instruments](https://mlsanity.com/paper/1610.07524/) (2016)
- [Inherent Trade-Offs in the Fair Determination of Risk Scores](https://mlsanity.com/paper/1609.05807/) (2016)
- [Algorithmic decision making and the cost of fairness](https://mlsanity.com/paper/1701.08230/) (2017)
- [FairFil: Contrastive Neural Debiasing Method for Pretrained Text Encoders](https://mlsanity.com/paper/2103.06413/) (2021)
- [A Confidence-Based Approach for Balancing Fairness and Accuracy](https://mlsanity.com/paper/1601.05764/) (2016)
- [Auditing Black-box Models for Indirect Influence](https://mlsanity.com/paper/1602.07043/) (2016)
- [A General Framework for Implicit and Explicit Debiasing of Distributional Word Vector Spaces](https://mlsanity.com/paper/1909.06092/) (2019)
- [Rank-Based Multi-task Learning for Fair Regression](https://mlsanity.com/paper/2009.11405/) (2020)
- [Obtaining Better Static Word Embeddings Using Contextual Embedding Models](https://mlsanity.com/paper/2106.04302/) (2021)
- [Fairness-Aware Neural R'eyni Minimization for Continuous Features](https://mlsanity.com/paper/1911.04929/) (2019)
- [Wasserstein-based fairness interpretability framework for machine learning models](https://mlsanity.com/paper/2011.03156/) (2020)
- [The Impact of Data Preparation on the Fairness of Software Systems](https://mlsanity.com/paper/1910.02321/) (2019)
- [DebIE: A Platform for Implicit and Explicit Debiasing of Word Embedding Spaces](https://mlsanity.com/paper/2103.06598/) (2021)
- [VERB: Visualizing and Interpreting Bias Mitigation Techniques for Word Representations](https://mlsanity.com/paper/2104.02797/) (2021)
- [Fair-Net: A Network Architecture For Reducing Performance Disparity Between Identifiable Sub-Populations](https://mlsanity.com/paper/2106.00720/) (2021)

## Built on by (most cited first, 1 of 1)

- [FAIR Enough: How Can We Develop and Assess a FAIR-Compliant Dataset for Large Language Models' Training?](https://mlsanity.com/paper/2401.11033/) (2024)

## Abstract (arXiv)

This paper summarizes and evaluates various approaches, methods, and techniques for pursuing fairness in artificial intelligence (AI) systems. It examines the merits and shortcomings of these measures and proposes practical guidelines for defining, measuring, and preventing bias in AI. In particular, it cautions against some of the simplistic, yet common, methods for evaluating bias in AI systems, and offers more sophisticated and effective alternatives. The paper also addresses widespread controversies and confusions in the field by providing a common language among different stakeholders of high-impact AI systems. It describes various trade-offs involving AI fairness, and provides practical recommendations for balancing them. It offers techniques for evaluating the costs and benefits of fairness targets, and defines the role of human judgment in setting these targets. This paper provides discussions and guidelines for AI practitioners, organization leaders, and policymakers, as well as various links to additional materials for a more technical audience. Numerous real-world examples are provided to clarify the concepts, challenges, and recommendations from a practical perspective.