Picture for Carlos Mougan

Carlos Mougan

Moral Persuasion in Large Language Models: Evaluating Susceptibility and Ethical Alignment

Add code
Nov 18, 2024
Viaarxiv icon

Model Agnostic Explainable Selective Regression via Uncertainty Estimation

Add code
Nov 15, 2023
Viaarxiv icon

Kantian Deontology Meets AI Alignment: Towards Morally Robust Fairness Metrics

Add code
Nov 09, 2023
Viaarxiv icon

How to Data in Datathons

Add code
Sep 19, 2023
Viaarxiv icon

Demographic Parity Inspector: Fairness Audits via the Explanation Space

Add code
Mar 14, 2023
Viaarxiv icon

Explanation Shift: Investigating Interactions between Models and Shifting Data Distributions

Add code
Mar 14, 2023
Viaarxiv icon

Introducing explainable supervised machine learning into interactive feedback loops for statistical production system

Add code
Feb 07, 2022
Viaarxiv icon

Monitoring Model Deterioration with Explainable Uncertainty Estimation via Non-parametric Bootstrap

Add code
Jan 27, 2022
Viaarxiv icon

Fairness implications of encoding protected categorical attributes

Add code
Jan 27, 2022
Figure 1 for Fairness implications of encoding protected categorical attributes
Figure 2 for Fairness implications of encoding protected categorical attributes
Figure 3 for Fairness implications of encoding protected categorical attributes
Figure 4 for Fairness implications of encoding protected categorical attributes
Viaarxiv icon

Quantile Encoder: Tackling High Cardinality Categorical Features in Regression Problems

Add code
May 27, 2021
Figure 1 for Quantile Encoder: Tackling High Cardinality Categorical Features in Regression Problems
Figure 2 for Quantile Encoder: Tackling High Cardinality Categorical Features in Regression Problems
Figure 3 for Quantile Encoder: Tackling High Cardinality Categorical Features in Regression Problems
Viaarxiv icon