Develops a causal framework unifying generative AI fairness with standard ML, with new decompositions, identification conditions, and estimators demonstrated on LLM race and gender bias.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
years
2026 2roles
background 2polarities
background 2representative citing papers
A non-parametric causal framework decomposes disparities in survival times into direct, indirect, and spurious pathway contributions using graphical models and the Causal Reduction Theorem.
citing papers explorer
-
Causal Bias Detection in Generative Artificial Intelligence
Develops a causal framework unifying generative AI fairness with standard ML, with new decompositions, identification conditions, and estimators demonstrated on LLM race and gender bias.
-
Causal Fairness for Survival Analysis
A non-parametric causal framework decomposes disparities in survival times into direct, indirect, and spurious pathway contributions using graphical models and the Causal Reduction Theorem.