Automatic Causal Fairness Analysis with LLM-Generated Reporting

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Berarducci, Alessia, Rossetto, Eric, Antonucci, Alessandro, Zaffalon, Marco
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917448275460096
author Berarducci, Alessia
Rossetto, Eric
Antonucci, Alessandro
Zaffalon, Marco
author_facet Berarducci, Alessia
Rossetto, Eric
Antonucci, Alessandro
Zaffalon, Marco
contents AutoML, intended as the process of automating the application of machine learning to real-world problems, is a key step for AI popularisation. Most AutoML frameworks are not accounting for the potential lack of fairness in the training data and in the corresponding predictions. We introduce \textsc{FairMind}, a software prototype aiming to automatise fairness analysis at the dataset level. We achieve that by resorting to the assumptions of the \emph{standard fairness model}, recently proposed by Plečko and Bareinboim. This allows for a sound fairness evaluation in terms of causal effects, based on \emph{counterfactual} queries involving the target, possibly confounders and mediators, and the different values of an input feature we regard as \emph{protected}. After the necessary data preprocessing, the tool implements a closed-form computation of the effects. LLMs are consequently exploited to generate accurate reports on the fairness levels detected in the training dataset. We achieve that in a zero-shot setup and show by examples the expected advantages with respect to a direct analysis performed by the LLM. To favour applications, extensions to ordinal protected variable and continuous targets and novel decomposition results are also discussed.
format Preprint
id arxiv_https___arxiv_org_abs_2604_27011
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Automatic Causal Fairness Analysis with LLM-Generated Reporting
Berarducci, Alessia
Rossetto, Eric
Antonucci, Alessandro
Zaffalon, Marco
Machine Learning
Artificial Intelligence
AutoML, intended as the process of automating the application of machine learning to real-world problems, is a key step for AI popularisation. Most AutoML frameworks are not accounting for the potential lack of fairness in the training data and in the corresponding predictions. We introduce \textsc{FairMind}, a software prototype aiming to automatise fairness analysis at the dataset level. We achieve that by resorting to the assumptions of the \emph{standard fairness model}, recently proposed by Plečko and Bareinboim. This allows for a sound fairness evaluation in terms of causal effects, based on \emph{counterfactual} queries involving the target, possibly confounders and mediators, and the different values of an input feature we regard as \emph{protected}. After the necessary data preprocessing, the tool implements a closed-form computation of the effects. LLMs are consequently exploited to generate accurate reports on the fairness levels detected in the training dataset. We achieve that in a zero-shot setup and show by examples the expected advantages with respect to a direct analysis performed by the LLM. To favour applications, extensions to ordinal protected variable and continuous targets and novel decomposition results are also discussed.
title Automatic Causal Fairness Analysis with LLM-Generated Reporting
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2604.27011