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.
M., Sarro, F., and Harman, M
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 3roles
background 1polarities
background 1representative citing papers
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.
FairLogue shows that intersectional disparities in two clinical prediction tasks are largely consistent with randomized group membership.
citing papers explorer
-
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.
-
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.
-
FairLogue: Evaluating Intersectional Fairness across Clinical Machine Learning Use Cases using the All of Us Research Program
FairLogue shows that intersectional disparities in two clinical prediction tasks are largely consistent with randomized group membership.