# Evaluating AI Group Fairness: a Fuzzy Logic Perspective

arXiv: https://arxiv.org/abs/2406.18939 · HTML: https://mlsanity.com/paper/2406.18939/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 61 references that are in the map.
- First posted on arXiv 27 Jun 2024.

## Builds on (most cited first, 22 of 22)

- [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)
- [Counterfactual Fairness](https://mlsanity.com/paper/1703.06856/) (2017)
- [Inherent Trade-Offs in the Fair Determination of Risk Scores](https://mlsanity.com/paper/1609.05807/) (2016)
- [Fairness Beyond Disparate Treatment & Disparate Impact: Learning Classification without Disparate Mistreatment](https://mlsanity.com/paper/1610.08452/) (2016)
- [Algorithmic Recourse: from Counterfactual Explanations to Interventions](https://mlsanity.com/paper/2002.06278/) (2020)
- [Empirical Risk Minimization under Fairness Constraints](https://mlsanity.com/paper/1802.08626/) (2018)
- [Trustworthy AI: From Principles to Practices](https://mlsanity.com/paper/2110.01167/) (2021)
- [Counterfactual Explanations and Algorithmic Recourses for Machine Learning: A Review](https://mlsanity.com/paper/2010.10596/) (2020)
- [Fairness in Machine Learning: Lessons from Political Philosophy](https://mlsanity.com/paper/1712.03586/) (2017)
- [Aequitas: A Bias and Fairness Audit Toolkit](https://mlsanity.com/paper/1811.05577/) (2018)
- [An Intersectional Definition of Fairness](https://mlsanity.com/paper/1807.08362/) (2018)
- [Why Fairness Cannot Be Automated: Bridging the Gap Between EU Non-Discrimination Law and AI](https://mlsanity.com/paper/2005.05906/) (2020)
- [Socially Responsible AI Algorithms: Issues, Purposes, and Challenges](https://mlsanity.com/paper/2101.02032/) (2021)
- [Rethinking Fairness: An Interdisciplinary Survey of Critiques of Hegemonic ML Fairness Approaches](https://mlsanity.com/paper/2205.04460/) (2022)
- [The four-fifths rule is not disparate impact: a woeful tale of epistemic trespassing in algorithmic fairness](https://mlsanity.com/paper/2202.09519/) (2022)
- [Preference-Informed Fairness](https://mlsanity.com/paper/1904.01793/) (2019)
- [Counterfactual Fairness Is Basically Demographic Parity](https://mlsanity.com/paper/2208.03843/) (2022)
- [Multi-dimensional discrimination in Law and Machine Learning -- A comparative overview](https://mlsanity.com/paper/2302.05995/) (2023)
- [Personalized Algorithmic Recourse with Preference Elicitation](https://mlsanity.com/paper/2205.13743/) (2022)
- [Fuzzy Logic and Probability](https://mlsanity.com/paper/1302.4953/) (2013)
- [Toward A Logical Theory Of Fairness and Bias](https://mlsanity.com/paper/2306.13659/) (2023)

## Abstract (arXiv)

Artificial intelligence systems often address fairness concerns by evaluating and mitigating measures of group discrimination, for example that indicate biases against certain genders or races. However, what constitutes group fairness depends on who is asked and the social context, whereas definitions are often relaxed to accept small deviations from the statistical constraints they set out to impose. Here we decouple definitions of group fairness both from the context and from relaxation-related uncertainty by expressing them in the axiomatic system of Basic fuzzy Logic (BL) with loosely understood predicates, like encountering group members. We then evaluate the definitions in subclasses of BL, such as Product or Lukasiewicz logics. Evaluation produces continuous instead of binary truth values by choosing the logic subclass and truth values for predicates that reflect uncertain context-specific beliefs, such as stakeholder opinions gathered through questionnaires. Internally, it follows logic-specific rules to compute the truth values of definitions. We show that commonly held propositions standardize the resulting mathematical formulas and we transcribe logic and truth value choices to layperson terms, so that anyone can answer them. We also use our framework to study several literature definitions of algorithmic fairness, for which we rationalize previous expedient practices that are non-probabilistic and show how to re-interpret their formulas and parameters in new contexts.