EPS Dashboard

Authors: Drago Plecko

Summary

The paper extends causal fairness methodology from standard supervised ML (where you learn a single predictor) to generative AI, where models can sample from arbitrary conditionals and implicitly construct beliefs about all causal mechanisms, not just a single outcome. The author formalizes causal fairness for generative AI, derives new decomposition results that quantify fairness impacts along (a) different causal pathways and (b) the replacement of real-world mechanisms by the generative model's mechanisms, establishes identification conditions, and introduces efficient estimators. Empirical analysis demonstrates race and gender bias in large language models across datasets.

Main takeaways:

Generative AI fairness is fundamentally different from standard ML fairness: generative models construct beliefs about all causal mechanisms, not just a single predictor.
The paper unifies causal fairness for generative AI and standard ML under a common theoretical framework.
New causal decomposition results enable granular quantification of bias along causal pathways and due to mechanism replacement.
Identification conditions and efficient estimators are provided for causal fairness quantities.
Empirical analysis reveals race and gender bias in LLMs across different datasets.

Relevance

Not directly related to my persona installation research, but conceptually interesting: the idea that generative models construct their own beliefs about causal mechanisms (rather than inheriting them from data) parallels how fine-tuning might install or replace behavioral mechanisms. Could be relevant if I formalize persona installation as mechanism replacement.

Threat model

Potential threat/caveat for clean result "Fine-tuning one persona on a two-marker chunk and another on the start marker plants the end marker at every donor answer's end, not chained to the start (LOW confidence)": this item discusses bias.

Abstract

arXiv:2605.11365v1 Announce Type: cross Abstract: Automated systems built on artificial intelligence (AI) are increasingly deployed across high-stakes domains, raising critical concerns about fairness and the perpetuation of demographic disparities that exist in the world. In this context, causal inference provides a principled framework for reasoning about fairness, as it links observed disparities to underlying mechanisms and aligns naturally with human intuition and legal notions of discrimination. Prior work on causal fairness primarily focuses on the standard machine learning setting, where a decision-maker constructs a single predictive mechanism $f_{\widehat Y}$ for an outcome variable $Y$, while inheriting the causal mechanisms of all other covariates from the real world. The generative AI setting, however, is markedly more complex: generative models can sample from arbitrary conditionals over any set of variables, implicitly constructing their own beliefs about all causal mechanisms rather than learning a single predictive function. This fundamental difference requires new developments in causal fairness methodology. We formalize the problem of causal fairness in generative AI and unify it with the standard ML setting under a common theoretical framework. We then derive new causal decomposition results that enable granular quantification of fairness impacts along both (a) different causal pathways and (b) the replacement of real-world mechanisms by the generative model's mechanisms. We establish identification conditions and introduce efficient estimators for causal quantities of interest, and demonstrate the value of our methodology by analyzing race and gender bias in large language models across different datasets.