Picture for Alexandra Chouldechova

Alexandra Chouldechova

Machine Unlearning Doesn't Do What You Think: Lessons for Generative AI Policy, Research, and Practice

Add code
Dec 09, 2024
Viaarxiv icon

A Framework for Evaluating LLMs Under Task Indeterminacy

Add code
Nov 21, 2024
Viaarxiv icon

SureMap: Simultaneous Mean Estimation for Single-Task and Multi-Task Disaggregated Evaluation

Add code
Nov 14, 2024
Viaarxiv icon

A structured regression approach for evaluating model performance across intersectional subgroups

Add code
Jan 26, 2024
Viaarxiv icon

The Impact of Differential Feature Under-reporting on Algorithmic Fairness

Add code
Jan 16, 2024
Viaarxiv icon

Multi-Target Multiplicity: Flexibility and Fairness in Target Specification under Resource Constraints

Add code
Jun 23, 2023
Viaarxiv icon

Examining risks of racial biases in NLP tools for child protective services

Add code
May 30, 2023
Viaarxiv icon

Algorithmic Fairness and Vertical Equity: Income Fairness with IRS Tax Audit Models

Add code
Jun 20, 2022
Figure 1 for Algorithmic Fairness and Vertical Equity: Income Fairness with IRS Tax Audit Models
Figure 2 for Algorithmic Fairness and Vertical Equity: Income Fairness with IRS Tax Audit Models
Figure 3 for Algorithmic Fairness and Vertical Equity: Income Fairness with IRS Tax Audit Models
Figure 4 for Algorithmic Fairness and Vertical Equity: Income Fairness with IRS Tax Audit Models
Viaarxiv icon

Imagining new futures beyond predictive systems in child welfare: A qualitative study with impacted stakeholders

Add code
May 18, 2022
Figure 1 for Imagining new futures beyond predictive systems in child welfare: A qualitative study with impacted stakeholders
Figure 2 for Imagining new futures beyond predictive systems in child welfare: A qualitative study with impacted stakeholders
Figure 3 for Imagining new futures beyond predictive systems in child welfare: A qualitative study with impacted stakeholders
Figure 4 for Imagining new futures beyond predictive systems in child welfare: A qualitative study with impacted stakeholders
Viaarxiv icon

Doubting AI Predictions: Influence-Driven Second Opinion Recommendation

Add code
Apr 29, 2022
Figure 1 for Doubting AI Predictions: Influence-Driven Second Opinion Recommendation
Figure 2 for Doubting AI Predictions: Influence-Driven Second Opinion Recommendation
Viaarxiv icon