Safety, Ethics & Governance · intermediate · concept 278 of 311 · Updated Nov 4, 2026
AI Bias & Fairness
AI systems can perpetuate and amplify societal biases present in training data. Understanding, measuring, and mitigating bias is critical for responsible AI deployment. Formal fairness metrics (demographic parity, equalized odds, predictive parity) famously conflict: satisfying all of them at once is mathematically impossible in most real settings.
L1 · Everyday userDevelopersTech leadersLeadershipProduct leadersNon-technicalQA and testingSEO and content
Top AI contributors on this
- Fei-Fei LiWorld Labs / Stanford University
- Timnit GebruDistributed AI Research Institute (DAIR)
- Margaret MitchellHugging Face
- Sara HookerAdaption Labs
- Yejin ChoiStanford University
- Yi ZengBeijing Institute of AI Safety and Governance / Renmin University of China
Key terms
Training data biasAlgorithmic fairnessDisparate impactFairlearnDemographic parityEqualized odds
Where you meet it in the real world
Hiring algorithms, criminal justice, lending decisions, healthcare
Videos
▶ Algorithmic Bias in AI: What It Is and How to Fix It ↗
IBM Technology · YouTube
▶ Unraveling AI Bias: Principles & Practices ↗
IBM Technology · YouTube
Guides and articles
Courses, papers, and more
This unlocks