Fairness & Bias
Group and individual criteria, impossibility results, measurement under missing attributes, and mitigation costs.
5concepts
60flashcards
36minutes of reading
- 01 Where Bias Enters the Pipeline The six distinct points at which disparity is introduced, why calling them all "biased data" prevents fixing them, and which stage each mitigation actually addresses.
- 02 Bias in Generative Models Why classification fairness metrics do not transfer to open-ended generation, the harm categories that appear instead, and the evaluation approaches that produce actionable findings.
- 03 Group Fairness Criteria and Why They Conflict Demographic parity, equalised odds and calibration stated precisely, the impossibility result showing you cannot have all three, and what choosing between them commits you to.
- 04 Measuring Fairness Without the Attribute The methods for estimating disparity when group membership is unavailable, why proxy inference introduces error in a direction that matters, and how to report a result built on an estimate.
- 05 Mitigation at Pre-, In- and Post-Processing The three points at which a fairness intervention can act, what each costs in accuracy and in flexibility, and the legal constraint that decides which are available.