Triage scores extend risk scores via additive counterfactual utilities to incorporate intervention effects in high-stakes decisions.
The measure and mismeasure of fairness: A critical review of fair machine learning
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
representative citing papers
Empirical audit of LAION-2B-en and LAION-2B-multi finds overrepresentation of young adults, White people, and males plus stereotypical emotion associations across two attribute classifiers.
Introduces ETHICS benchmark showing current language models have promising but incomplete ability to predict basic human ethical judgments on text scenarios.
Causality resolves trade-offs in trustworthy AI by treating them as invariance conflicts under different data-generating process changes.
Unfairness appears as unfair causal paths in a causal Bayesian network of the data process, providing a graphical tool to measure bias and build fair models in complex cases.
Graphical models show Equalized Odds and related fairness criteria to be misleading, so fairness assessments should be case-specific and depend on the algorithm's information flow.
citing papers explorer
-
Triage Score: A Counterfactual Risk Assessment Instrument
Triage scores extend risk scores via additive counterfactual utilities to incorporate intervention effects in high-stakes decisions.
-
Unmasking LAION-5B: Age, Gender, Race, and Emotion Biases in Large-Scale Image Datasets
Empirical audit of LAION-2B-en and LAION-2B-multi finds overrepresentation of young adults, White people, and males plus stereotypical emotion associations across two attribute classifiers.
-
Aligning AI With Shared Human Values
Introduces ETHICS benchmark showing current language models have promising but incomplete ability to predict basic human ethical judgments on text scenarios.
-
Trustworthy AI Suffers from Invariance Conflicts and Causality is The Solution
Causality resolves trade-offs in trustworthy AI by treating them as invariance conflicts under different data-generating process changes.
-
A Causal Bayesian Networks Viewpoint on Fairness
Unfairness appears as unfair causal paths in a causal Bayesian network of the data process, providing a graphical tool to measure bias and build fair models in complex cases.
-
Fairness criteria through the lens of directed acyclic graphical models
Graphical models show Equalized Odds and related fairness criteria to be misleading, so fairness assessments should be case-specific and depend on the algorithm's information flow.