# AI Biases as Asymmetries: A Review to Guide Practice

arXiv: https://arxiv.org/abs/2503.07326 · HTML: https://mlsanity.com/paper/2503.07326/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 17 of its 67 references that are in the map.
- First posted on arXiv 10 Mar 2025.

## Builds on (most cited first, 17 of 17)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Fair prediction with disparate impact: A study of bias in recidivism prediction instruments](https://mlsanity.com/paper/1610.07524/) (2016)
- [Bias and Fairness in Large Language Models: A Survey](https://mlsanity.com/paper/2309.00770/) (2023)
- [Inherent Trade-Offs in the Fair Determination of Risk Scores](https://mlsanity.com/paper/1609.05807/) (2016)
- [A Framework for Understanding Sources of Harm throughout the Machine Learning Life Cycle](https://mlsanity.com/paper/1901.10002/) (2019)
- [REVISE: A Tool for Measuring and Mitigating Bias in Visual Datasets](https://mlsanity.com/paper/2004.07999/) (2020)
- [NLPositionality: Characterizing Design Biases of Datasets and Models](https://mlsanity.com/paper/2306.01943/) (2023)
- [Fairness And Bias in Artificial Intelligence: A Brief Survey of Sources, Impacts, And Mitigation Strategies](https://mlsanity.com/paper/2304.07683/) (2023)
- [A Perspective on Explainable Artificial Intelligence Methods: SHAP and LIME](https://mlsanity.com/paper/2305.02012/) (2023)
- [A Closer Look at Benchmarking Self-Supervised Pre-training with Image Classification](https://mlsanity.com/paper/2407.12210/) (2024)
- [Unmasking Conversational Bias in AI Multiagent Systems](https://mlsanity.com/paper/2501.14844/) (2025)
- [MBIAS: Mitigating Bias in Large Language Models While Retaining Context](https://mlsanity.com/paper/2405.11290/) (2024)
- [Why we need biased AI -- How including cognitive and ethical machine biases can enhance AI systems](https://mlsanity.com/paper/2203.09911/) (2022)
- [End-To-End Bias Mitigation: Removing Gender Bias in Deep Learning](https://mlsanity.com/paper/2104.02532/) (2021)
- [The Futility of Bias-Free Learning and Search](https://mlsanity.com/paper/1907.06010/) (2019)
- [Detection and Mitigation of Algorithmic Bias via Predictive Rate Parity](https://mlsanity.com/paper/2204.05947/) (2022)
- [Navigating Ensemble Configurations for Algorithmic Fairness](https://mlsanity.com/paper/2210.05594/) (2022)

## Abstract (arXiv)

The understanding of bias in AI is currently undergoing a revolution. Initially understood as errors or flaws, biases are increasingly recognized as integral to AI systems and sometimes preferable to less biased alternatives. In this paper, we review the reasons for this changed understanding and provide new guidance on two questions: First, how should we think about and measure biases in AI systems, consistent with the new understanding? Second, what kinds of bias in an AI system should we accept or even amplify, and what kinds should we minimize or eliminate, and why? The key to answering both questions, we argue, is to understand biases as "violations of a symmetry standard" (following Kelly). We distinguish three main types of asymmetry in AI systems-error biases, inequality biases, and process biases-and highlight places in the pipeline of AI development and application where bias of each type is likely to be good, bad, or inevitable.