mlsanityData to 7 Oct 2026

AI Biases as Asymmetries: A Review to Guide Practice

arXiv 2503.07326 ↗First posted 10 Mar 2025cs.CY cs.AI cs.LGcited by 0

Not on the map. Why?

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 17 of its 67 references that are in the map. First posted on arXiv 10 Mar 2025.

Builds on

17 of 67 references.

References · 17

  1. 2017Attention Is All You Needcited by 59,932
  2. 2016Fair prediction with disparate impact: A study of bias in recidivism prediction instrumentscited by 671
  3. 2023Bias and Fairness in Large Language Models: A Surveycited by 626
  4. 2016Inherent Trade-Offs in the Fair Determination of Risk Scorescited by 582
  5. 2019A Framework for Understanding Sources of Harm throughout the Machine Learning Life Cyclecited by 192
  6. 2020REVISE: A Tool for Measuring and Mitigating Bias in Visual Datasetscited by 136
  7. 2023NLPositionality: Characterizing Design Biases of Datasets and Modelscited by 91
  8. 2023Fairness And Bias in Artificial Intelligence: A Brief Survey of Sources, Impacts, And Mitigation Strategiescited by 83
  9. 2023A Perspective on Explainable Artificial Intelligence Methods: SHAP and LIMEcited by 42
  10. 2024A Closer Look at Benchmarking Self-Supervised Pre-training with Image Classificationcited by 19
  11. 2025Unmasking Conversational Bias in AI Multiagent Systemscited by 16
  12. 2024MBIAS: Mitigating Bias in Large Language Models While Retaining Contextcited by 15
5 more
  1. 2022Why we need biased AI -- How including cognitive and ethical machine biases can enhance AI systemscited by 7
  2. 2021End-To-End Bias Mitigation: Removing Gender Bias in Deep Learningcited by 6
  3. 2019The Futility of Bias-Free Learning and Searchcited by 5
  4. 2022Detection and Mitigation of Algorithmic Bias via Predictive Rate Paritycited by 4
  5. 2022Navigating Ensemble Configurations for Algorithmic Fairnesscited by 1

Built on by

Not cited yet.