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.
M., Sarro, F., and Harman, M
4 Pith papers cite this work, alongside 24 external citations. Polarity classification is still indexing.
4
Pith papers citing it
24
external citations · external index
citation-role summary
background 1
citation-polarity summary
years
2026 4roles
background 1polarities
background 1representative citing papers
The thesis presents a kernel method for multiaccuracy across overlooked subpopulations, information-theoretic optimal watermarking for LLMs, and a simulator showing LLM agents outperforming humans in supply chains while creating tail risks.
Intersectional fairness audits of two clinical models on All of Us found larger subgroup gaps than single-axis checks, yet counterfactuals suggested most gaps matched randomized group membership.
FairLogue provides modular tools to quantify intersectional fairness gaps in clinical ML using extended demographic parity, equalized odds, and counterfactual methods, shown on a glaucoma surgery prediction task from All of Us data.
citing papers explorer
-
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.
-
Trustworthy AI: Ensuring Reliability and Accountability from Models to Agents
The thesis presents a kernel method for multiaccuracy across overlooked subpopulations, information-theoretic optimal watermarking for LLMs, and a simulator showing LLM agents outperforming humans in supply chains while creating tail risks.
-
Evaluating Intersectional Fairness across Clinical Machine Learning Use Cases using Fairlogue and the All of Us Research Program
Intersectional fairness audits of two clinical models on All of Us found larger subgroup gaps than single-axis checks, yet counterfactuals suggested most gaps matched randomized group membership.
-
FairLogue: A Toolkit for Intersectional Fairness Analysis in Clinical Machine Learning Models
FairLogue provides modular tools to quantify intersectional fairness gaps in clinical ML using extended demographic parity, equalized odds, and counterfactual methods, shown on a glaucoma surgery prediction task from All of Us data.