FairMind: A Tool for Automatic Causal Fairness Analysis with LLM-Generated Reports

Alessia Berarducci, Eric Rossetto, Alessandro Antonucci, Marco Zaffalon
Proceedings of Fifth European Conference on Algorithmic Fairness, PMLR 350:159-164, 2026.

Abstract

We introduce FairMind, a software tool designed to automate fairness analysis at the dataset level. Our approach builds on the assumptions of the \emph{standard fairness model} recently proposed by Plečko and Bareinboim, enabling a principled evaluation of fairness in terms of causal effects. The analysis relies on \emph{counterfactual} queries involving the target variable, potential mediators and confounders and different values of an input feature treated as \emph{protected}. Following the necessary data preprocessing, the tool performs closed-form computations of these effects. Large language models (LLMs) are then employed to generate detailed and interpretable reports on the fairness properties identified in the training data. Even in zero-shot settings, our approach offers substantial advantages over direct LLM-based analyses, particularly as the complexity of the data structures increases.

Cite this Paper

BibTeX
@InProceedings{pmlr-v350-berarducci26a, title = {FairMind: A Tool for Automatic Causal Fairness Analysis with LLM-Generated Reports}, author = {Berarducci, Alessia and Rossetto, Eric and Antonucci, Alessandro and Zaffalon, Marco}, booktitle = {Proceedings of Fifth European Conference on Algorithmic Fairness}, pages = {159--164}, year = {2026}, editor = {De Bie, Tijl and Defrance, MaryBeth and Calders, Toon and Nguyen, Dennis}, volume = {350}, series = {Proceedings of Machine Learning Research}, month = {02--04 Sep}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v350/main/assets/berarducci26a/berarducci26a.pdf}, url = {https://proceedings.mlr.press/v350/berarducci26a.html}, abstract = {We introduce FairMind, a software tool designed to automate fairness analysis at the dataset level. Our approach builds on the assumptions of the \emph{standard fairness model} recently proposed by Plečko and Bareinboim, enabling a principled evaluation of fairness in terms of causal effects. The analysis relies on \emph{counterfactual} queries involving the target variable, potential mediators and confounders and different values of an input feature treated as \emph{protected}. Following the necessary data preprocessing, the tool performs closed-form computations of these effects. Large language models (LLMs) are then employed to generate detailed and interpretable reports on the fairness properties identified in the training data. Even in zero-shot settings, our approach offers substantial advantages over direct LLM-based analyses, particularly as the complexity of the data structures increases.} }
Endnote
%0 Conference Paper %T FairMind: A Tool for Automatic Causal Fairness Analysis with LLM-Generated Reports %A Alessia Berarducci %A Eric Rossetto %A Alessandro Antonucci %A Marco Zaffalon %B Proceedings of Fifth European Conference on Algorithmic Fairness %C Proceedings of Machine Learning Research %D 2026 %E Tijl De Bie %E MaryBeth Defrance %E Toon Calders %E Dennis Nguyen %F pmlr-v350-berarducci26a %I PMLR %P 159--164 %U https://proceedings.mlr.press/v350/berarducci26a.html %V 350 %X We introduce FairMind, a software tool designed to automate fairness analysis at the dataset level. Our approach builds on the assumptions of the \emph{standard fairness model} recently proposed by Plečko and Bareinboim, enabling a principled evaluation of fairness in terms of causal effects. The analysis relies on \emph{counterfactual} queries involving the target variable, potential mediators and confounders and different values of an input feature treated as \emph{protected}. Following the necessary data preprocessing, the tool performs closed-form computations of these effects. Large language models (LLMs) are then employed to generate detailed and interpretable reports on the fairness properties identified in the training data. Even in zero-shot settings, our approach offers substantial advantages over direct LLM-based analyses, particularly as the complexity of the data structures increases.
APA
Berarducci, A., Rossetto, E., Antonucci, A. & Zaffalon, M.. (2026). FairMind: A Tool for Automatic Causal Fairness Analysis with LLM-Generated Reports. Proceedings of Fifth European Conference on Algorithmic Fairness, in Proceedings of Machine Learning Research 350:159-164 Available from https://proceedings.mlr.press/v350/berarducci26a.html.

Related Material