Automatic Causal Fairness Analysis with LLM-Generated Reporting

TL;DR

This paper presents FairMind, a tool that automates causal fairness analysis at the dataset level using counterfactual queries and LLMs to generate reports, enhancing fairness evaluation in AutoML.

Contribution

Introducing FairMind, a novel software prototype that automates causal fairness analysis with LLM-generated reporting based on the standard fairness model.

Findings

FairMind performs sound fairness evaluation using counterfactual effects.

LLMs can generate accurate fairness reports in a zero-shot setup.

Extensions to ordinal and continuous variables are discussed.

Abstract

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 Ple\v{c}ko 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.